# Image processing

Image processing is the field concerned with manipulating and analyzing digital images by computer, using techniques such as spatial and frequency-domain operations, signal processing, and reconstruction algorithms.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings

DevFeed: [Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings](<https://devfeed.tech/articles/erasing-the-wrong-thing-conditional-attribute-leakage-and-concept-erasure-in-shared-foundation-model-embeddings-145084.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25640>)

Author: Haijun He, Fei Li, Donghong Ji, Junjun He

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [association](<https://devfeed.tech/tags/association.md>), [attack](<https://devfeed.tech/tags/attack.md>), [biomedical](<https://devfeed.tech/tags/biomedical.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [linear](<https://devfeed.tech/tags/linear.md>), [model](<https://devfeed.tech/tags/model.md>), [strata](<https://devfeed.tech/tags/strata.md>), [utility](<https://devfeed.tech/tags/utility.md>)

### AI overview

Population-level concept erasure can leave sensitive attributes detectable within task groups when task and sensitive labels are associated. The authors prove that global and task-conditional linear guardedness cannot both preserve a nonzero linear task signal under this association. They introduce TC-LEACE, which enforces linear guardedness within each task stratum. Across four vision models and 85 CelebA attribute pairs, conditional leakage persisted after LEACE, with the gap between marginal and conditional audits growing with association strength; a pre-erasure-statistics estimate tracked observed utility costs. In chest-radiograph experiments using three models, chest-tube status remained detectable within diagnosis strata after LEACE, even though a marginal attack performed worse than a diagnosis-only reference. TC-LEACE recovered most of LEACE's linear task-utility loss while keeping conditional leakage within a prespecified margin of LEACE's.

### Source excerpt

arXiv:2611.25640v1 Announce Type: cross Abstract: Medical-image embeddings are increasingly shared in place of raw images for authorized downstream tasks, yet they may reveal sensitive attributes. Standard concept-erasure methods target population-level guardedness. However, we prove that, when binary task and sensitive labels are associated, global and task-conditional linear guardedness cannot both hold while a nonzero linear task signal is preserved, so global erasure must either eliminate that signal or retain task-conditional linear leakage. We further show how global erasure affects linear readers' discrimination between positive and negative samples with different sensitive attributes, deriving an approximate closed-form prediction of its utility cost from pre-erasure statistics. Motivated by this conflict, we introduce Task-Conditional LEACE (TC-LEACE), a closed-form variant of LEACE that enforces linear guardedness within each task stratum of its fitting data. We evaluate four vision foundation models on 85 CelebA attribute pairs spanning a broad range of associations. After LEACE, conditional leakage persists across all four encoders, the discrepancy between marginal and conditional audits increases with association strength, and predicted utility costs track observed losses. We then examine hospital chest radiographs using three foundation models, including two biomedical models, in which chest-tube status is strongly associated with diagnosis. Although a marginal attack on LEACE-erased embeddings underperforms a diagnosis-only reference, chest-tube status remains detectable within diagnosis strata. TC-LEACE recovers most of LEACE's linear task-utility loss while keeping task-conditional leakage within a prespecified margin of LEACE's.

## Digitization of Analogue Gauges using Computer Vision

DevFeed: [Digitization of Analogue Gauges using Computer Vision](<https://devfeed.tech/articles/digitization-of-analogue-gauges-using-computer-vision-145647.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26262>)

Author: Erico Kayumba Mutonkole, Olasupo Ajayi, Omowunmi Isafiade

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [gauge](<https://devfeed.tech/tags/gauge.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [residual](<https://devfeed.tech/tags/residual.md>), [web-scraping](<https://devfeed.tech/tags/web-scraping.md>)

### AI overview

The study reports that OpenCV with ResNet18 achieved 97.3% accuracy in reading analogue pressure gauges, compared with 64.4% for OpenCV with VGG19 and 63.8% for OpenCV with Scikit-Image. The comparison used 1,848 gauge images covering 0-10 BAR, assembled through web scraping, synthetic generation, and augmentation. These results favor the ResNet18 approach within the reported evaluation; the supplied abstract does not describe deployment performance.

### Source excerpt

arXiv:2611.26262v1 Announce Type: cross Abstract: Analogue gauges remain prevalent in manufacturing industries for measuring physical quantities, yet manual monitoring by operators introduces human error and operational inefficiency. This research developed and evaluated an automated gauge reading system using computer vision and deep learning techniques. Three hybrid approaches were implemented and compared: OpenCV with Scikit-Image (traditional computer vision), OpenCV with ResNet18, and OpenCV with VGG19 (deep learning approaches). A comprehensive dataset of 1,848 pressure gauge images (0-10 BAR range) was curated through web scraping, synthetic generation, and augmentation techniques. The experimental results demonstrate that ResNet18 significantly outperforms the alternatives, achieving an accuracy of 97.3%, compared to VGG19's 64.4% and Scikit-Image's 63.8%. The study validates the effectiveness of residual learning architectures for industrial gauge digitization, providing a robust foundation for Industry 5.0 automation applications.

## Inject Where It Matters: Objective-Dependent Feature Control in Rectified-Flow Image Editing

DevFeed: [Inject Where It Matters: Objective-Dependent Feature Control in Rectified-Flow Image Editing](<https://devfeed.tech/articles/inject-where-it-matters-objective-dependent-feature-control-in-rectified-flow-image-editing-145589.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25811>)

Author: Nina Goncharova, Alexandra Ivanova, Aibek Alanov

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [image editing](<https://devfeed.tech/topics/image-editing.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [bench](<https://devfeed.tech/tags/bench.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [feature-injection](<https://devfeed.tech/tags/feature-injection.md>), [flux](<https://devfeed.tech/tags/flux.md>), [image-editing](<https://devfeed.tech/tags/image-editing.md>), [inference](<https://devfeed.tech/tags/inference.md>), [masking](<https://devfeed.tech/tags/masking.md>), [masks](<https://devfeed.tech/tags/masks.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [top-k](<https://devfeed.tech/tags/top-k.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

The method controls source-feature injection in prompt-driven FLUX image editing through adaptive spatial masks and REINFORCE-selected Top-K transformer blocks. Masks gate injection using differences between source- and target-conditioned outputs at matched inversion states; selected blocks remain fixed at inference, with no online search. On PIE-Bench with FLUX.1-dev, masking controls the alignment-preservation trade-off. Across 60 validation examples, a learned nine-block set achieved lower whole-image LPIPS than RF-Edit's 18-block set in the same masked pipeline, with slightly lower alignment. It had the lowest LPIPS among 50 random nine-block sets, though not the highest reward. Objective sweeps favored different blocks for preservation and alignment.

### Source excerpt

arXiv:2611.25811v1 Announce Type: new Abstract: Many prompt-driven FLUX editing methods rely on injecting source features into target-conditioned generation, creating an inherent trade-off between source preservation and the desired edit. We address this problem by controlling where source features are injected and which transformer blocks are used. First, we introduce adaptive masks that spatially gate feature injection using differences between source- and target-conditioned block outputs at matched inversion states. Second, we use REINFORCE to select Top-K injection blocks under different preservation-editability objectives. The selected blocks are fixed at inference and require no online search. On PIE-Bench with FLUX.1-dev, spatial masking controls the alignment-preservation trade-off. On 60 validation examples, a learned nine-block set gives lower whole-image LPIPS than the 18-block RF-Edit set within the same masked pipeline, with slightly lower alignment. Among 50 random nine-block sets, it has the lowest LPIPS but not the highest reward. Separate objective sweeps reveal different block preferences for preservation and alignment.

## AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing

DevFeed: [AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing](<https://devfeed.tech/articles/aerobelief-budgeted-first-action-verification-for-evidence-guided-aerial-sensing-145539.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25568>)

Author: Tianren Li, Dongbo Li, Hongkai Chen, Jie Liu, Guoliang Xing

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [budgeting](<https://devfeed.tech/tags/budgeting.md>), [complete](<https://devfeed.tech/tags/complete.md>), [context](<https://devfeed.tech/tags/context.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dji](<https://devfeed.tech/tags/dji.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [hosted](<https://devfeed.tech/tags/hosted.md>), [image](<https://devfeed.tech/tags/image.md>), [image-processing](<https://devfeed.tech/tags/image-processing.md>), [imagery](<https://devfeed.tech/tags/imagery.md>), [queries](<https://devfeed.tech/tags/queries.md>), [reference](<https://devfeed.tech/tags/reference.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [target](<https://devfeed.tech/tags/target.md>), [verification](<https://devfeed.tech/tags/verification.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

AeroBelief verifies candidate aerial views by their next executable action: an inexpensive proposer scans grouped views, then a structured world model is queried selectively. Calibrated bounds and a six-query controller connect action selection to belief updates, acceptance checks, and scheduled sensing. In 960 executions across 40 worlds, it completed 75.42% of tasks, versus 73.33% with exhaustive world-model scoring and 65.83% with line-of-sight geometry, while using 91.81% fewer reference-candidate evaluations than exhaustive scoring. In fixed-reference replay, proposer-scaled bounds improved first-action certificate availability from 36.25% to 54.69% and cut mean queries per state by 13.54% versus unit-scale anchored bounds. A separate ground-hosted pipeline applied context-guided admission and feedback to 2,685 UAV images from seven routes: it retained all eight independently supported target confirmations while processing 76.05% fewer images and using 70.02% less active processing service than uncapped all-frame processing. These findings are reported for the described simulations and recorded imagery.

### Source excerpt

arXiv:2611.25568v1 Announce Type: new Abstract: Aerial sensing must combine uncertain overhead context with current observations while budgeting prediction, movement and image processing. AeroBelief uses the next executable action as the unit of verification against reference scores. It groups candidate views by first action, scans them with an inexpensive proposer, and selectively queries a structured world model (WM). Calibrated group bounds support strict commitment; a six-query controller connects selective prediction with belief updates, acceptance checks and scheduled sensing. Across four layout families, 40 worlds and 960 closed-loop executions, the AeroBelief controller completes 75.42% of tasks, compared with 73.33% for exhaustive WM scoring and 65.83% for line-of-sight geometry, using 91.81% fewer reference-candidate evaluations than exhaustive scoring. In fixed-reference replay with a six-query cap, proposer-scaled anchored bounds raised first-action certificate availability from 36.25% to 54.69% and reduced mean queries per state by 13.54% relative to unit-scale anchored bounds. A complete ground-hosted pipeline processes 2,685 self-collected 20-megapixel unmanned aerial vehicle (UAV) images from seven DJI Mavic 3M routes. Context-guided admission and feedback retain all eight independently supported target confirmations with 76.05% fewer processed images and 70.02% less accumulated active processing service than uncapped all-frame processing; feedback saves another 5.17% of images relative to static context. The studies connect budgeted action selection with evidence-driven processing of recorded flight imagery.

## A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps

DevFeed: [A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps](<https://devfeed.tech/articles/a-wolf-in-sheep-s-pixels-visual-camouflage-attacks-via-hdr-gain-maps-145517.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25469>)

Author: Qi Shen, Yujia Gong, Yue Zhao, Tong Liu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [hdr](<https://devfeed.tech/tags/hdr.md>), [maps](<https://devfeed.tech/tags/maps.md>), [processing](<https://devfeed.tech/tags/processing.md>), [sdr](<https://devfeed.tech/tags/sdr.md>)

### AI overview

DRJanus exploits the difference between SDR image processing and HDR display: automated systems may inspect an SDR base while viewers see a reconstruction that also uses an auxiliary gain map. It embeds two independently chosen color images in one JPEG without querying or optimizing against the target model, preserving the SDR base exactly and achieving an average HDR reconstruction PSNR of 43.03 dB across 400 images. In tests, it evaded all six commercial moderation services and nine vision-language models on a 100-image sexual-content benchmark. Across five agents, tested on 120 task cases per threat setting, attack success ranged from 31.67% to 100% for moderation evasion and 95% to 100% for task manipulation. The authors also explore cross-view consistency checks as a mitigation; the supplied abstract does not report their effectiveness.

### Source excerpt

arXiv:2611.25469v1 Announce Type: cross Abstract: An image can pass automated safety checks while showing harmful content to its human viewer. We introduce DRJanus, a visual camouflage attack that exploits the gap between standard dynamic range (SDR) processing and high dynamic range (HDR) display. Automated systems often read only an image's SDR base, whereas HDR viewers reconstruct its appearance using an auxiliary gain map. DRJanus inverts this reconstruction to embed two independently chosen color images in a single JPEG, without querying or optimizing against the target model. It preserves the chosen SDR base exactly and reconstructs HDR targets at an average PSNR of 43.03 dB across 400 images. On a benchmark of 100 sexual-content images, DRJanus evades detection by all six tested commercial moderation services and nine vision-language models. Across five agents, each evaluated on 120 task cases per threat setting, attack success ranges from 31.67% to 100% for moderation evasion and from 95% to 100% for task manipulation. We also explore cross-view consistency checks as a mitigation. These findings expose a gap in visual trust: securing what a machine reads does not secure what a user sees. A demo is available at https://qshen0629.github.io/DRJanus/

## Lightweight Low-Frequency Non-Intrusive Load Monitoring via Karhunen-Lo\\\`eve Feature Distillation and Temporal Convolutional Networks

DevFeed: [Lightweight Low-Frequency Non-Intrusive Load Monitoring via Karhunen-Lo\\\`eve Feature Distillation and Temporal Convolutional Networks](<https://devfeed.tech/articles/lightweight-low-frequency-non-intrusive-load-monitoring-via-karhunen-lo-eve-feature-distillation-and-temporal-convolutional-networks-145089.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25678>)

Author: Sanka Peeris, Pandula Thennakoon, Praveen Sumanasekara, Roshan Godaliyadda, Parakrama Ekanayake, Janaka Ekanayake

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>), [Time-sequences](<https://devfeed.tech/topics/time-sequences.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [disaggregation](<https://devfeed.tech/tags/disaggregation.md>), [edge](<https://devfeed.tech/tags/edge.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [energy](<https://devfeed.tech/tags/energy.md>), [features](<https://devfeed.tech/tags/features.md>), [filter](<https://devfeed.tech/tags/filter.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grid](<https://devfeed.tech/tags/grid.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [load](<https://devfeed.tech/tags/load.md>), [models](<https://devfeed.tech/tags/models.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [smart](<https://devfeed.tech/tags/smart.md>), [smart-grid](<https://devfeed.tech/tags/smart-grid.md>), [solution](<https://devfeed.tech/tags/solution.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

The proposed edge-oriented NILM framework pairs activity-boundary-aware augmentation--which recombines complete or near-complete appliance activation segments without requiring new fully labeled household aggregates--with KLT-derived temporal features and a compact TCN. On UK-DALE and REDD at 10-second sampling with leave-one-house-out testing, it reports disaggregation accuracy comparable to or better than NILMFormer, BERT4NILM, BiLSTM, and BiGRU. It uses 31,009 parameters, the fewest among the five compared models, and takes 2.78 ms per 1,000 samples on one CPU thread, reported as 84-95% less time than the baselines.

### Source excerpt

arXiv:2611.25678v1 Announce Type: cross Abstract: Non-Intrusive Load Monitoring (NILM) is a critical enabler for demand-side management which allows for smart grid optimization. A deployment-ready NILM solution necessitates three key features: accurate disaggregation, low-frequency sampling, and low computational cost. This paper proposes a lightweight, edge-oriented NILM framework that combines activity-boundary-aware synthetic data augmentation with Karhunen-Lo\`eve Transform (KLT) feature extraction and a Temporal Convolutional Network (TCN). The augmentation stage extracts and recombines complete or near-complete appliance activation segments so that the model can be trained without new fully labeled household aggregates. The KLT filter bank extracts decorrelated, appliance-informed temporal features which are then fed into a compact TCN along with the original aggregate for energy disaggregation. Evaluations on two standard NILM datasets, UK-DALE and REDD, at 10-s sampling and with leave-one-house-out testing, demonstrate that the proposed architecture achieves comparable or superior disaggregation accuracy relative to NILMFormer, BERT4NILM, BiLSTM, and BiGRU. The computational footprint of the framework is 31,009 parameters, the fewest of the five models compared, and on a single CPU thread it needs 2.78 ms per 1000 samples, 84-95% less than the baselines. These results demonstrate a favorable accuracy-efficiency tradeoff for low-frequency smart-meter NILM.

## Gaussian Primitive Fusion for Any-Resolution Multimodal Images

DevFeed: [Gaussian Primitive Fusion for Any-Resolution Multimodal Images](<https://devfeed.tech/articles/gaussian-primitive-fusion-for-any-resolution-multimodal-images-142761.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24164>)

Author: Baoshuo Cai, Xinrui Jiang, Bing Cao

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [artifacts](<https://devfeed.tech/tags/artifacts.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [images](<https://devfeed.tech/tags/images.md>), [infrared](<https://devfeed.tech/tags/infrared.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [resolutions](<https://devfeed.tech/tags/resolutions.md>), [super-resolution](<https://devfeed.tech/tags/super-resolution.md>), [textures](<https://devfeed.tech/tags/textures.md>)

### AI overview

Gaussian Primitive Fusion (GPF) combines multimodal images at differing native resolutions in a shared continuous Gaussian space, avoiding the initial resampling used by common-grid fusion. It fits native-resolution observations with shared Gaussian geometry and modality-specific content, learns their contributions in that representation, then renders the fused result at the finest native resolution. The abstract reports clearer contours and finer textures with fewer blurring and blocking artifacts than resample-then-fuse pipelines, and the best quantitative results across multiple infrared-visible benchmarks compared with state-of-the-art methods using interpolation or super-resolution frontends.

### Source excerpt

arXiv:2611.24164v1 Announce Type: cross Abstract: Multimodal image fusion integrates complementary observations from different modalities into a unified representation. Existing methods typically estimate modality contributions on a common discrete grid. When source modalities have different native resolutions, constructing such a grid generally involves resampling, which may introduce artifacts and affect subsequent fusion decisions. To address this problem, we propose Gaussian Primitive Fusion (GPF), which reformulates heterogeneous-resolution fusion in a shared continuous Gaussian space. Instead of first converting source images to a common resolution, GPF directly fits their native-resolution observations with shared Gaussian geometry and modality-specific content representations, and learns modality contributions within the resulting continuous representation. Once optimized, the fused representation is rendered at the finest native resolution without resampling the sources. With heterogeneous-resolution inputs, GPF produces clearer target contours and finer textures, with less blurring and blocking artifacts than resample-then-fuse pipelines. Quantitatively, it achieves the best results on multiple infrared-visible benchmarks against state-of-the-art fusion methods equipped with interpolation or super-resolution frontends.

## I2I Backdoor: Backdoor Attacks against Image-to-Image Tasks

DevFeed: [I2I Backdoor: Backdoor Attacks against Image-to-Image Tasks](<https://devfeed.tech/articles/i2i-backdoor-backdoor-attacks-against-image-to-image-tasks-142489.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2407.10445>)

Author: Wenbo Jiang, Hongwei Li, Jiaming He, Rui Zhang, Guowen Xu, Tianwei Zhang, Rongxing Lu

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [based](<https://devfeed.tech/tags/based.md>), [better](<https://devfeed.tech/tags/better.md>), [can](<https://devfeed.tech/tags/can.md>), [choice](<https://devfeed.tech/tags/choice.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [deep](<https://devfeed.tech/tags/deep.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [image](<https://devfeed.tech/tags/image.md>), [image-to-image](<https://devfeed.tech/tags/image-to-image.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

The paper proposes a backdoor for image-to-image networks that behaves normally on clean inputs but produces a specific inappropriate output when a universal adversarial perturbation trigger is present. Its training uses multi-task learning with dynamic weighting. The authors also show that denoised trigger-bearing images can fool downstream image classifiers and object detectors, and report effectiveness across state-of-the-art I2I architectures and robustness against different backdoor defenses. The supplied text is an abstract, so it does not provide implementation details or quantify these results.

### Source excerpt

arXiv:2407.10445v2 Announce Type: replace-cross Abstract: With the rapid development of deep learning technology, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks like image super-resolution and denoising. Despite their remarkable performance, the security of I2I networks has not been thoroughly investigated. While some studies have probed their susceptibility to adversarial attacks, none have explored the backdoor attack against I2I networks, which is a more stealthy and severe threat. In this work, for the first time, we comprehensively investigate the vulnerability of I2I networks to backdoor attacks. We propose a backdoor attack against I2I tasks, where the backdoored I2I network behaves normally on clean input images, yet outputs a specific inappropriate image when the backdoor trigger appears on the input image. To achieve such an I2I backdoor attack, we design a universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the trigger for the I2I backdoor. Besides, multi-task learning (MTL) with dynamic weighting methods is employed in the backdoor training process to gain better results. Expanding our focus beyond I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and object detection. Specifically, the backdoor-triggered image processed by the backdoored image denoising network can fool the downstream image classifiers and object detectors. Extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures as well as the robustness against different backdoor defenses.

## Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement

DevFeed: [Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement](<https://devfeed.tech/articles/multimodal-information-fusion-for-chart-understanding-a-survey-of-mllms-evolution-limitations-and-cognitive-enhancement-142507.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.10138>)

Author: Zhihang Yi, Jian Zhao, Jiancheng Lv, Tao Wang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Data visualization](<https://devfeed.tech/topics/data-visualization.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [charts](<https://devfeed.tech/tags/charts.md>), [components](<https://devfeed.tech/tags/components.md>), [core](<https://devfeed.tech/tags/core.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [information](<https://devfeed.tech/tags/information.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [survey](<https://devfeed.tech/tags/survey.md>)

### AI overview

The survey organizes research on chart understanding as the fusion of graphical and linguistic information. It maps downstream tasks and datasets, distinguishing canonical from non-canonical benchmarks, and traces methods from classic deep learning to MLLM approaches using more sophisticated fusion strategies. It identifies perceptual and reasoning deficits as key limitations of current models and points to advanced alignment and reinforcement learning as possible directions for cognitive enhancement. The supplied text is the abstract, so it does not provide the survey's detailed taxonomy or evidence for comparing specific methods.

### Source excerpt

arXiv:2602.10138v2 Announce Type: replace-cross Abstract: Chart understanding is a quintessential information fusion task, requiring the seamless integration of graphical and textual data to extract meaning. The advent of Multimodal Large Language Models (MLLMs) has revolutionized this domain, yet the landscape of MLLM-based chart analysis remains fragmented and lacks systematic organization. This survey provides a comprehensive roadmap of this nascent frontier by structuring the domain's core components. We begin by analyzing the fundamental challenges of fusing visual and linguistic information in charts. We then categorize downstream tasks and datasets, introducing a novel taxonomy of canonical and non-canonical benchmarks to highlight the field's expanding scope. Subsequently, we present a comprehensive evolution of methodologies, tracing the progression from classic deep learning techniques to state-of-the-art MLLM paradigms that leverage sophisticated fusion strategies. By critically examining the limitations of current models, particularly their perceptual and reasoning deficits, we identify promising future directions, including advanced alignment techniques and reinforcement learning for cognitive enhancement. This survey aims to equip researchers and practitioners with a structured understanding of how MLLMs are transforming chart information fusion and to catalyze progress toward more robust and reliable systems.

## OracleZoom: Reference-Constrained Recursive Image Super-Resolution Beyond Ground Truth

DevFeed: [OracleZoom: Reference-Constrained Recursive Image Super-Resolution Beyond Ground Truth](<https://devfeed.tech/articles/oraclezoom-reference-constrained-recursive-image-super-resolution-beyond-ground-truth-142557.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.06490>)

Author: Shubhashis Roy Dipta, Nobin Sarwar, Md Rizwan Parvez

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>)

Tags: [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [image](<https://devfeed.tech/tags/image.md>), [super-resolution](<https://devfeed.tech/tags/super-resolution.md>)

### AI overview

OracleZoom trains recursive super-resolution beyond available ground truth by feeding a prediction back into the model for a 4x->16x step, then projecting the 16x output back to the last 4x ground-truth image for a cross-scale constraint. Since that constraint checks only coarse content, a no-reference quality objective guides fine detail, while a latent prior is used to limit hallucinated artifacts. Across seven datasets, it reports the highest CLIPIQA at every zoom depth (mean 0.713 versus 0.621 for Chain-of-Zoom), with the largest gains at deeper zooms, despite training only to 16x and optimizing a different quality metric. Two pooled ground-truth-anchored judges found the same hallucination rate as Chain-of-Zoom at 16x and a lower rate at 4x; removing the cross-scale loss increased hallucination at 16x.

### Source excerpt

arXiv:2609.06490v2 Announce Type: replace-cross Abstract: Recursive image Super-Resolution (SR) reaches extreme magnification by feeding each prediction back into the same model, like zooming into an image again and again. Real ground truth for deep zooms is impractical to capture (a full $256\times$ target would be a 52 GB image), so predictions at deeper zooms have no supervision. Yet the last ground-truth image still contains the region that every deeper zoom magnifies. OracleZoom turns this region into a training signal. Inspired by on-policy self-distillation, the model trains on its own prediction for one recursive step ($4\times \rightarrow 16\times$), and a cross-scale loss projects each $16\times$ prediction back to the last ground truth at $4\times$. This projection can verify only coarse content, so a no-reference quality objective guides the remaining fine detail, and a latent prior stops this objective from adding hallucinated artifacts. On seven datasets, OracleZoom achieves the highest CLIPIQA at every zoom depth (mean 0.713 vs. 0.621 for Chain-of-Zoom), with the largest gains at the deepest zooms, even though training stops at $16\times$ and optimizes a different quality metric. Pooled over two ground-truth-anchored judges, this added detail comes at the same hallucination rate as Chain-of-Zoom at $16\times$ and a lower rate at $4\times$, and removing the cross-scale loss raises hallucination at $16\times$.

## SpiderMark: Hybrid Watermarking for Generative AI via Algorithmic Injection and Learning-Based Verification

DevFeed: [SpiderMark: Hybrid Watermarking for Generative AI via Algorithmic Injection and Learning-Based Verification](<https://devfeed.tech/articles/spidermark-hybrid-watermarking-for-generative-ai-via-algorithmic-injection-and-learning-based-verification-142765.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24200>)

Author: Chihcheng Hsieh, Yang Song, Flora Salim, Martin Bell, Jacinto C. Nascimento, Catarina Moreira

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [fourier analysis](<https://devfeed.tech/topics/fourier-analysis.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-content](<https://devfeed.tech/tags/ai-content.md>), [ai-generated-images](<https://devfeed.tech/tags/ai-generated-images.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [clip](<https://devfeed.tech/tags/clip.md>), [coco](<https://devfeed.tech/tags/coco.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [confidence-score](<https://devfeed.tech/tags/confidence-score.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [detection](<https://devfeed.tech/tags/detection.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [verification](<https://devfeed.tech/tags/verification.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

SpiderMark embeds a structured spider-web pattern--radial spokes and concentric polygonal rings--into the Fourier representation of diffusion models' initial latent noise, then uses a lightweight ResNet-18 verifier with PSNR and L1 cues to produce a continuous watermark confidence score. It requires no changes to pretrained model weights. The abstract reports the highest fixed-threshold accuracy in eight of nine evaluation conditions and strong detection on unseen COCO prompts without verifier retraining. CLIP similarity and FID measurements show small measured differences in prompt alignment and distributional image quality. These claims are based on the supplied abstract; detailed evaluation conditions and results are not provided.

### Source excerpt

arXiv:2611.24200v1 Announce Type: cross Abstract: The proliferation of diffusion-based generative models has intensified the need for reliable methods to trace and verify the provenance of AI-generated images. Existing watermarking approaches for diffusion models typically rely on isotropic frequency patterns and handcrafted detection metrics, which are prone to directional vulnerability and threshold instability across diverse image transformations. We propose SpiderMark, a hybrid watermarking framework that combines algorithmic frequency-domain injection with learning-based probabilistic verification, requiring no modifications to pretrained diffusion model weights. SpiderMark embeds a structured spider-web pattern, comprising radial spokes and concentric polygonal rings, into the Fourier representation of the initial latent noise, and trains a lightweight ResNet-18 verifier augmented with auxiliary similarity cues (PSNR and L1) to produce a continuous watermark confidence score for watermark detection. Across nine evaluation conditions, SpiderMark achieves the highest fixed-threshold Accuracy in eight, while retaining strong detection on unseen COCO prompts without verifier retraining. CLIP similarity and FID measurements show that these detection gains are accompanied by small measured differences in prompt alignment and distributional image quality. SpiderMark establishes that structured watermark geometry and learned probabilistic verification can be unified into a single, practical framework, bridging the gap between imperceptibility, robustness, and real-world verifiability for generative AI content attribution.

## Asymmetric Optical Image Watermarking

DevFeed: [Asymmetric Optical Image Watermarking](<https://devfeed.tech/articles/asymmetric-optical-image-watermarking-143120.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23350>)

Author: Guang Yang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [fourier transform](<https://devfeed.tech/topics/fourier-transform.md>), [ed25519](<https://devfeed.tech/topics/ed25519.md>), [public key](<https://devfeed.tech/topics/public-key.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [ed25519](<https://devfeed.tech/tags/ed25519.md>), [image](<https://devfeed.tech/tags/image.md>), [optical](<https://devfeed.tech/tags/optical.md>), [security](<https://devfeed.tech/tags/security.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

The proposed watermark combines publicly verifiable authorship with a secret-key optical carrier. Its first layer binds an Ed25519 signature to image content in Fourier magnitudes, allowing offline verification with a public key. The second uses a secret phase hologram to write a carrier detected by a matched-filter correlator. In scalar-diffraction simulations, the optical signer closely reproduced the digital pipeline and verified at least 99.5% of 877 images in each of eight post-sensor settings, while accepting none of 40,670 unmarked images. The carrier was detected on 99.8% of unattacked images with the matched key, but detection fell to zero with a 1% scale error or a one-bin mask shift. These are simulation results; no hardware was built. The authors distinguish security claims based on signature and content binding from measured optical performance.

### Source excerpt

arXiv:2611.23350v1 Announce Type: new Abstract: Watermark detectors held by a provider cannot be checked by third parties, and a party that can detect a mark can usually also forge it. We study a two-layer image watermark in which the Fourier transform at the core of the pipeline is performed by a coherent optical 4F unit. Layer 1 carries an Ed25519 signature bound to the image content in Fourier magnitudes, so anyone with the public key verifies offline. Layer 2 is a key-defined carrier written by a secret phase hologram and read by a matched-filter correlator. The optics is a scalar-diffraction simulation with finite modulator bits, pixel aperture, pupil, defocus, misalignment, and sensor noise. No hardware is built. All criteria were fixed in a hashed specification before any optical result. The simulated optical signer reproduces the digital pipeline (field error 1.7e-15, bit agreement 99.997%), verifies at least 99.5% of 877 images under each of 8 post-sensor settings, one unattacked, and accepts none of 40,670 unmarked images. The optical carrier is key-selective: the matched key detects it on 99.8% of the unattacked images, and detection falls to 0% under a scale error of 1% and to 0% under a mask shift of 1 bin. Security rests on the signature and the content binding, for which we separate what is provable from what is measured.

## Image Watermarking With Memory Across Reissuance

DevFeed: [Image Watermarking With Memory Across Reissuance](<https://devfeed.tech/articles/image-watermarking-with-memory-across-reissuance-142646.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23363>)

Author: Xinyuan Li, Yi Nian, Xiaoqin Feng, Tiankai Yang, Yue Zhao

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [image](<https://devfeed.tech/tags/image.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [region](<https://devfeed.tech/tags/region.md>), [releases](<https://devfeed.tech/tags/releases.md>), [revision](<https://devfeed.tech/tags/revision.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

Generational Stratigraphy Fields (GSF) track whether an image is current, superseded, or unissued and identify the last authorized revision of each region. GSF combines watermark evidence with an authenticated live reference to the current release, allowing publishers to replace or retire releases without altering already circulated copies. On 480 histories spanning four releases, it classified issued images as current or superseded with 99.67% accuracy and recalled 94.09% of unissued edits. After three reissues, regional generation labels reached 93.13% median accuracy, and latest approved regions were localized at 92.86% IoU. Tested delivery transformations left regional labels readable while impairing issued-state recognition.

### Source excerpt

arXiv:2611.23363v1 Announce Type: cross Abstract: Publishers often revise and reissue images, yet valid watermarks may persist on superseded releases or unapproved edits. Even a current release can contain regions last authorized at different revisions. We introduce and formalize reissuable provenance: determining an image's current, superseded, or unissued status and recovering each region's last authorized revision (its generation), with abstention when evidence is insufficient. Generational Stratigraphy Fields (GSF) combine watermark evidence with an authenticated live reference to the current release, enabling replacement or retirement without rewriting circulated copies. Each reissue freshly embeds new generation labels in approved regions and inherited labels elsewhere, preserving history without requiring old watermarks to survive successive edits. Our complete-output reissuance evaluation follows 480 histories through four releases, retaining each AI editor's entire output. GSF achieves 99.67% accuracy in classifying issued images as current or superseded and 94.09% recall of unissued edits. After three reissues, one generation map provides time and location: it recovers regional labels with 93.13% median accuracy and localizes the latest approved revision with 92.86% IoU. Regional labels remain readable under tested delivery transformations that impair issued-state recognition. Watermarks can thus express who issued an image, which release is authoritative now, and when each region was last authorized.

## FlashReFocus: Interactive Image Refocusing in Seconds

DevFeed: [FlashReFocus: Interactive Image Refocusing in Seconds](<https://devfeed.tech/articles/flashrefocus-interactive-image-refocusing-in-seconds-142577.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.23297>)

Author: Ching-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang, Xin Li, Chih-Chung Hsu

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>), [image editing](<https://devfeed.tech/topics/image-editing.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [camera](<https://devfeed.tech/tags/camera.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [image](<https://devfeed.tech/tags/image.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [lens](<https://devfeed.tech/tags/lens.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [rtx-pro-6000](<https://devfeed.tech/tags/rtx-pro-6000.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

FlashReFocus makes repeated refocusing edits faster and more consistent by running diffusion once to reconstruct an all-in-focus image, then using a lightweight network to render each edit. Its explicit defocus map controls blur, while defocus-bias attention connects tokens with similar blur magnitudes; editing the map also enables tilt-shift and two-plane effects. The one-step deblurrer and decoder refiner aim to balance detail, fidelity, and perceptual quality. On zero-shot bokeh rendering, it leads the evaluated methods in fidelity and perceptual quality on EBB! Val176 and 3CReal, a benchmark of 89 pairs from three camera-lens systems. At 1536x1536, the reported full refocus time is 2.45 seconds and each subsequent edit takes 0.46 seconds on one RTX PRO 6000.

### Source excerpt

arXiv:2610.23297v2 Announce Type: replace-cross Abstract: Single-image refocusing changes the focal plane and depth of field of a photograph after capture. Users compare focal choices on one photograph, so content stability across edits matters alongside quality and speed. Recent generative methods rerun large diffusion models for every edit, even when they first restore an all-in-focus image, so content can change inconsistently between edits. Yet only this restoration is highly ill-posed and benefits from a generative prior, whereas rendering blur is largely determined by depth and the focal plane. We therefore propose FlashReFocus, which runs diffusion once per photograph and renders each edit with a lightweight network. A one-step diffusion deblurrer with a decoder refiner recovers fine detail efficiently while balancing fidelity and perceptual quality. The renderer uses an explicit defocus map for control and defocus-bias attention to promote information exchange between tokens with similar blur magnitudes. Because every edit reuses the same reconstruction, in-focus content stays consistent across edits, and editing the map enables tilt-shift and two-plane effects. We further collect 3CReal, a benchmark of 89 pairs from three camera-lens systems, to evaluate generalization to unseen optics. For zero-shot bokeh rendering on EBB! Val176 and 3CReal, FlashReFocus leads the evaluated methods in fidelity and perceptual quality. At 1536x1536, a complete refocus takes 2.45 s and each subsequent edit 0.46 s on one RTX PRO 6000.

## Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models

DevFeed: [Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models](<https://devfeed.tech/articles/analyzing-learned-convnet-features-with-dirichlet-process-gaussian-mixture-models-139737.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/1702.07189>)

Author: David Malmgren-Hansen, Allan Aasbjerg Nielsen, Rasmus Engholm

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [clustering](<https://devfeed.tech/tags/clustering.md>), [convolutional-neural-networks](<https://devfeed.tech/tags/convolutional-neural-networks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [transfer-learning](<https://devfeed.tech/tags/transfer-learning.md>), [visualization](<https://devfeed.tech/tags/visualization.md>)

### AI overview

The paper proposes visualizing learned Convnet representations by clustering internal features with a Dirichlet Process Gaussian Mixture Model. It addresses the difficulty of interpreting high-dimensional representations and abstract deep layers by clustering representations across all nodes of each layer. The abstract identifies transfer learning--using a model trained on one dataset for a task on another--as a context where this visualization may be useful, but gives no further method details or reported results.

### Source excerpt

arXiv:1702.07189v1 Announce Type: cross Abstract: Convolutional Neural Networks (Convnets) have achieved good results in a range of computer vision tasks the recent years. Though given a lot of attention, visualizing the learned representations to interpret Convnets, still remains a challenging task. The high dimensionality of internal representations and the high abstractions of deep layers are the main challenges when visualizing Convnet functionality. We present in this paper a technique based on clustering internal Convnet representations with a Dirichlet Process Gaussian Mixture Model, for visualization of learned representations in Convnets. Our method copes with the high dimensionality of a Convnet by clustering representations across all nodes of each layer. We will discuss how this application is useful when considering transfer learning, i.e.\ transferring a model trained on one dataset to solve a task on a different one.

## QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems

DevFeed: [QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems](<https://devfeed.tech/articles/qutcc-quantile-uncertainty-training-and-conformal-calibration-for-imaging-inverse-problems-139744.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2507.14760>)

Author: Cassandra Tong Ye, Shamus Li, Tyler King, Kristina Monakhova

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [conformal-prediction](<https://devfeed.tech/tags/conformal-prediction.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [imaging](<https://devfeed.tech/tags/imaging.md>), [magnetic](<https://devfeed.tech/tags/magnetic.md>), [medical-imaging](<https://devfeed.tech/tags/medical-imaging.md>), [microscopy](<https://devfeed.tech/tags/microscopy.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [quantile](<https://devfeed.tech/tags/quantile.md>), [regression](<https://devfeed.tech/tags/regression.md>), [training](<https://devfeed.tech/tags/training.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

QUTCC addresses oversized uncertainty intervals in image-valued conformal prediction by accounting for spatial variation during calibration. A U-Net with quantile embeddings learns conditional quantiles, which are then used for nonlinear, spatially adaptive conformal calibration. At test time it estimates intervals with pixel-marginal coverage guarantees and can also produce pixel-wise conditional density estimates without built-in distributional assumptions. Across denoising, accelerated MRI, and quantitative phase microscopy, the authors report tighter intervals than prior conformal methods at the same coverage and plausible conditional distributions; in some cases, high-uncertainty regions help locate hallucinations. The supplied text is an abstract and does not provide implementation details or quantitative comparisons.

### Source excerpt

arXiv:2507.14760v3 Announce Type: replace-cross Abstract: While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty estimation techniques, such as conformal prediction, can help by predicting statistically valid error bars for a model's prediction. However, popular conformal prediction methods were not designed for high-dimensional image-valued problems and do not take into account spatial correlations within an image during conformal calibration, resulting in larger-than-necessary uncertainty intervals. We propose a practical simultaneous quantile regression method that enables non-linear, spatially-adaptive scaling during conformal calibration. Our method, QUTCC uses a U-Net architecture with a quantile embedding to learn a full conditional quantile distribution during training, and then leverages this non-linear, learned function for spatially-adaptive conformal calibration. At test time, our method can efficiently estimate uncertainty intervals with pixel-marginal coverage guarantees. In addition, QUTCC can also predict pixel-wise conditional probability density estimates without any built-in distributional assumptions. We evaluate our method on several denoising problems, accelerated magnetic resonance imaging, and quantitative phase microscopy. Our method consistently produces tighter uncertainty intervals than prior conformal methods at the same coverage level, can predict plausible conditional distributions for different tasks, and in some cases, high-uncertainty regions can help us locate hallucinations in a model's prediction.

## FaceRiff: Data-Efficient Unified Text-to-3D Face Asset Synthesis via Geometric Conditioning

DevFeed: [FaceRiff: Data-Efficient Unified Text-to-3D Face Asset Synthesis via Geometric Conditioning](<https://devfeed.tech/articles/faceriff-data-efficient-unified-text-to-3d-face-asset-synthesis-via-geometric-conditioning-139922.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21867>)

Author: Elly Akhoundi, Mathieu Lamarre, Thibault Goyallon, Patrick Anderson, \\'Etienne Danvoye

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [peft](<https://devfeed.tech/topics/peft.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [asset](<https://devfeed.tech/tags/asset.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [image](<https://devfeed.tech/tags/image.md>), [independent](<https://devfeed.tech/tags/independent.md>), [lighting](<https://devfeed.tech/tags/lighting.md>), [lora](<https://devfeed.tech/tags/lora.md>), [maps](<https://devfeed.tech/tags/maps.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [text](<https://devfeed.tech/tags/text.md>)

### AI overview

FaceRiff generates text-conditioned 3D face assets--mesh, albedo, and displacement--in a shared UV space, using a pretrained SDXL model with task-specific LoRA adapters and UV normal maps for geometric conditioning. It was trained on 2,049 scans from about 350 identities on a single GPU, updating less than 3% of backbone parameters per task, and produces assets without per-instance optimization. The abstract reports greater per-prompt diversity than FaceG2E and DreamFace while maintaining prompt alignment and fixed-topology UV consistency; it also generates lighting-independent albedo for PBR relighting and pore-scale displacement. In a blind study of 45 industry professionals, perceived realism was substantially higher than DreamFace and approached that of real captures.

### Source excerpt

arXiv:2611.21867v1 Announce Type: cross Abstract: High-resolution facial datasets with consistent UV-mapped geometry, albedo, and physically based displacement are scarce, yet such assets are essential for photorealistic digital-human rendering. Existing 3D face generation methods are often slow, single-modality, or require large specialized datasets. Meanwhile, large image diffusion models encode strong facial priors but do not natively produce lighting-independent textures, pore-scale displacement, or UV-aligned geometry. We present FaceRiff, a unified, data- and parameter-efficient framework for generating complete 3D face assets (mesh, albedo, and displacement) directly from text in a shared UV space. FaceRiff adapts a pretrained SDXL backbone with task-specific LoRA adapters and uses UV normal maps as geometric conditioning: per-instance normals guide albedo and displacement synthesis, while a dataset-mean normal provides a canonical spatial anchor for mesh generation. Using only 2,049 scans from approximately 350 identities and training on a single GPU, FaceRiff updates less than 3% of the backbone parameters per task and produces render-ready 3D face assets without per-instance optimization. Compared with FaceG2E and DreamFace, FaceRiff produces greater per-prompt diversity while preserving prompt alignment and fixed-topology UV consistency, and additionally generates lighting-independent albedo suitable for PBR relighting and pore-scale displacement absent from prior text-driven baselines. A blind study with 45 industry professionals shows that FaceRiff achieves substantially higher perceived realism than DreamFace, approaching that of real captures. Overall, FaceRiff demonstrates that pretrained diffusion priors can be adapted to unified 3D face asset synthesis under limited data.

## Temporal Diffusion Models for Joint Signal-Channel Estimation under Gaussian and $\\alpha$-Stable MIMO Channels

DevFeed: [Temporal Diffusion Models for Joint Signal-Channel Estimation under Gaussian and $\\alpha$-Stable MIMO Channels](<https://devfeed.tech/articles/temporal-diffusion-models-for-joint-signal-channel-estimation-under-gaussian-and-alpha-stable-mimo-channels-141785.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22548>)

Author: Rawad Kansoh, Bahaa Ammoury, Charbel Hannoun, Jihad Fahs, Ibrahim Abou-Faycal

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [alpha](<https://devfeed.tech/tags/alpha.md>), [channel](<https://devfeed.tech/tags/channel.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [mimo](<https://devfeed.tech/tags/mimo.md>), [stable](<https://devfeed.tech/tags/stable.md>)

### AI overview

The study applies diffusion-based reconstruction to pilot-based channel estimation and joint image-channel recovery in MIMO systems with Gaussian or symmetric α-stable fading. It guides reverse diffusion with the observation likelihood; for blind recovery, separate image and channel models are combined through that guidance. The authors report that a trained diffusion model can be reused across a location-scale family without retraining. Under a time-dependent channel model, using information from earlier observations improves channel estimates and reconstructed image quality. For the same heavy-tailed channel data, an α-stable diffusion prior outperforms a Gaussian prior on both reported measures.

### Source excerpt

arXiv:2611.22548v1 Announce Type: cross Abstract: Diffusion models have emerged as powerful tools for learning complex data distributions and solving inverse problems. However, most diffusion models rely on the Gaussian distribution, which does not accurately represent heavy-tailed data. In this work, we study diffusion-based reconstruction under Gaussian and symmetric $\alpha$-stable fading channels, while also exploring the benefits of using possible temporal dependence in the channel. We consider two variants: pilot-based channel-only estimation and joint image-channel recovery for MIMO systems. Our approach is based on several standard and score-based diffusion models for both Gaussian and $\alpha$-stable distributions. We refine these models by guiding the reverse diffusion process using the observation likelihood and show how a single trained diffusion model can be reused for the location-scale family of distributions without retraining. In blind MIMO recovery, separate diffusion models are used for the image and channel, and their estimates are combined through likelihood guidance. For each setting, we compare independent and temporal reconstruction, where information from previous observations is used to improve the estimation. We show that, under a time-dependent channel model, such a temporal reconstruction improves channel estimation and the quality of the reconstructed image. Finally, we show that, for the same heavy-tailed channel data, using an $\alpha$-stable diffusion prior provides better channel estimation and image reconstruction than using a Gaussian diffusion prior.

## FM-Mamba: An Efficient Native 2D Selective State Space Model with Stability-Aware Discretization

DevFeed: [FM-Mamba: An Efficient Native 2D Selective State Space Model with Stability-Aware Discretization](<https://devfeed.tech/articles/fm-mamba-an-efficient-native-2d-selective-state-space-model-with-stability-aware-discretization-139954.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22061>)

Author: Shengyuan Hu, Yiyong Sun, Weihang Shan, Yongzhe Chang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Mamba](<https://devfeed.tech/topics/mamba.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [delta](<https://devfeed.tech/tags/delta.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [grid](<https://devfeed.tech/tags/grid.md>), [images](<https://devfeed.tech/tags/images.md>), [independent](<https://devfeed.tech/tags/independent.md>), [inference](<https://devfeed.tech/tags/inference.md>), [input](<https://devfeed.tech/tags/input.md>), [local](<https://devfeed.tech/tags/local.md>), [mamba](<https://devfeed.tech/tags/mamba.md>), [model](<https://devfeed.tech/tags/model.md>), [native](<https://devfeed.tech/tags/native.md>), [position](<https://devfeed.tech/tags/position.md>), [projection](<https://devfeed.tech/tags/projection.md>), [ratio](<https://devfeed.tech/tags/ratio.md>), [scan](<https://devfeed.tech/tags/scan.md>), [space](<https://devfeed.tech/tags/space.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [stable](<https://devfeed.tech/tags/stable.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

FM-Mamba processes 2D features directly on the grid using a coupled Fornasini-Marchesini recurrence, avoiding feature-map flattening. Two position- and direction-dependent step sizes govern propagation along the spatial axes, while cross-axis coupling adds a diagonal-predecessor term. A normalized ratio gives a piecewise stability bound; steps outside it are projected back, and the criterion is checked per position after training to suppress systematic local amplification without global damping. A dual-diagonal wavefront scan gathers from two anti-diagonals, with one input projection per current state. The supplied abstract describes the mechanism but provides no benchmark results or quantitative performance comparisons.

### Source excerpt

arXiv:2611.22061v1 Announce Type: cross Abstract: When applied to two-dimensional features such as images, Mamba-based methods either flatten the feature map into 1D sequences and fuse multiple scans, which breaks spatial adjacency and multiplies computation, or recurse directly on the 2D grid but rescale the recurrence with a fixed input-independent factor and aggregate only the predecessors on a single anti-diagonal, leaving the discrete step unconstrained by 2D stability theory. We propose \textbf{FM-Mamba}, a native 2D selective state space model built on the general Fornasini--Marchesini (FM) model. Its coupled recurrence evolves along both spatial axes; cross-axis coupling induces a discrete diagonal-predecessor term $\tilde A_0$, and two independent input-dependent step sizes $\Delta_1(i,j)$, $\Delta_2(i,j)$ govern propagation along the two axes, so that the coefficients adapt per position and per direction. A normalized ratio $r_k=a_{0,k}/(a_{1,k}a_{2,k})$ yields a closed-form piecewise bound on the two step sizes; when a configuration falls outside the stable interval the steps are projected onto this bound, and the criterion is re-verified per position after training, which suppresses systematic local amplification without global damping. The recurrence is executed by a dual-diagonal wavefront scan: each update gathers information from two anti-diagonals, and the input enters the current state through a single projection, so that neither training nor inference flattens the feature map. Code is available at https://github.com/BitSsm/FM-Mamba-Runtime

## LeViT-UNet++: Towards Balanced Fine-Grained Details and Context for Efficient Medical Image Segmentation

DevFeed: [LeViT-UNet++: Towards Balanced Fine-Grained Details and Context for Efficient Medical Image Segmentation](<https://devfeed.tech/articles/levit-unet-towards-balanced-fine-grained-details-and-context-for-efficient-medical-image-segmentation-140035.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22482>)

Author: Guoping Xu, Jinling Zhu, Liuyue Li

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [balance](<https://devfeed.tech/tags/balance.md>), [context](<https://devfeed.tech/tags/context.md>), [convolution](<https://devfeed.tech/tags/convolution.md>), [convolutional-neural-networks](<https://devfeed.tech/tags/convolutional-neural-networks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [details](<https://devfeed.tech/tags/details.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [encoder-decoder](<https://devfeed.tech/tags/encoder-decoder.md>), [fast](<https://devfeed.tech/tags/fast.md>), [feature](<https://devfeed.tech/tags/feature.md>), [features](<https://devfeed.tech/tags/features.md>), [fine](<https://devfeed.tech/tags/fine.md>), [fps](<https://devfeed.tech/tags/fps.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [image](<https://devfeed.tech/tags/image.md>), [medical](<https://devfeed.tech/tags/medical.md>)

### AI overview

LeViT-UNet++ combines Haar wavelet multi-scale downsampling with a depthwise convolution decoder to preserve structural detail while fusing local spatial features with global representations from Transformer blocks. The authors report evaluation on Synapse, ACDC, LA2018, and MSD Heart in 2D and 3D settings, with competitive accuracy, compact size, and fast inference. On Synapse, it achieves a 76.57% DSC with 8.025M parameters at 241.72 FPS. The supplied abstract does not provide comparative results for the other benchmarks.

### Source excerpt

arXiv:2611.22482v1 Announce Type: cross Abstract: Efficient medical image segmentation is essential for clinical applications requiring fast and accurate delineation, such as surgical navigation, radiation therapy, and real-time image-guided intervention. Despite substantial advances in convolutional neural networks and Transformers, attaining high accuracy under limited computational resources remains difficult, because reducing model complexity often sacrifices fine-grained structural details and global context modeling, yielding an unfavorable accuracy-efficiency trade-off. To address this, we propose LeViT-UNet++, an efficient encoder-decoder architecture that better balances local detail preservation and global context modeling. Specifically, we introduce a Haar Wavelet Multi-Scale Downsampling (HWMD) module that decomposes feature representations into low- and high-frequency components to extract multi-scale structural information, thereby mitigating detail loss during downsampling. We further develop a depthwise convolution-based decoder that integrates multi-scale global representations from Transformer blocks with local spatial features, enabling progressive feature refinement while reducing computational overhead. Evaluated on four benchmarks (Synapse, ACDC, LA2018, and MSD Heart) under both 2D and 3D settings, LeViT-UNet++ achieves competitive accuracy with a compact parameter footprint and fast inference. On Synapse, for instance, it attains a DSC of 76.57% with only 8.025M parameters and 241.72 FPS, confirming a favorable accuracy-efficiency balance. These results demonstrate the effectiveness of combining wavelet-based multi-scale feature extraction with lightweight local-global feature fusion for efficient medical segmentation. The source code is available at https://github.com/apple1986/levit_unet_pp.

## Fast and Strong Image Protection against Diffusion Personalization

DevFeed: [Fast and Strong Image Protection against Diffusion Personalization](<https://devfeed.tech/articles/fast-and-strong-image-protection-against-diffusion-personalization-141490.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22494>)

Author: Jiwon Park, Jihye Kang, Namhyuk Ahn

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [cost](<https://devfeed.tech/tags/cost.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [fast](<https://devfeed.tech/tags/fast.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [image](<https://devfeed.tech/tags/image.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [projection](<https://devfeed.tech/tags/projection.md>), [protection](<https://devfeed.tech/tags/protection.md>)

### AI overview

The protective diffusion model (PDM) generates image-protection perturbations through denoising, avoiding the from-scratch optimization required for each image. It is trained to distill an iterative teacher, then post-trained using target residual projection (TRP) loss as a reward. The abstract reports that PDM outperforms nine baselines on faces and artworks and nearly matches its teacher at one-tenth the cost. These findings are limited to the abstract excerpt.

### Source excerpt

arXiv:2611.22494v1 Announce Type: cross Abstract: Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from scratch, so its cost grows with the number of images. We present the protective diffusion model (PDM), which is trained once and samples the perturbation of a new image over many denoising steps. PDM distills an iterative teacher and is then post-trained with the target residual projection (TRP) loss as a reward, a stronger objective than existing ones. PDM outperforms nine baselines on faces and artworks and nearly matches its teacher at a tenth of the cost.

## PRUE: A Practical Recipe for Field Boundary Segmentation at Scale

DevFeed: [PRUE: A Practical Recipe for Field Boundary Segmentation at Scale](<https://devfeed.tech/articles/prue-a-practical-recipe-for-field-boundary-segmentation-at-scale-141546.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.27101>)

Author: Gedeon Muhawenayo, Caleb Robinson, Subash Khanal, Zhanpei Fang, Isaac Corley, Alexander Wollam, Tianyi Gao, Leonard Strnad, Ryan Avery, Lyndon Estes, Ana M. T\\'arano, Nathan Jacobs, Hannah Kerner

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [geospatial](<https://devfeed.tech/topics/geospatial.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [all](<https://devfeed.tech/tags/all.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [changes](<https://devfeed.tech/tags/changes.md>), [combines](<https://devfeed.tech/tags/combines.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deep](<https://devfeed.tech/tags/deep.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [design](<https://devfeed.tech/tags/design.md>), [field](<https://devfeed.tech/tags/field.md>), [practical](<https://devfeed.tech/tags/practical.md>), [recipe](<https://devfeed.tech/tags/recipe.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

On the Fields of The World benchmark, a U-Net semantic segmentation model outperformed the evaluated instance-based and geospatial foundation models across performance and deployment metrics. The authors' approach combines a U-Net backbone with composite loss functions and targeted data augmentations to improve robustness to real-world variation. It reports 76% IoU and 47% object-F1, gains of 6 and 9 percentage points over the previous baseline, respectively. The abstract says the work releases all models and model-derived field-boundary datasets for five countries.

### Source excerpt

arXiv:2603.27101v3 Announce Type: replace-cross Abstract: Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illumination, spatial scale, and changes in geographic location. We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation using the Fields of The World (FTW) benchmark. We evaluate 18 models under unified experimental settings, showing that a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics. We propose a new segmentation approach that combines a U-Net backbone, composite loss functions, and targeted data augmentations to enhance performance and robustness under real-world conditions. Our model achieves a 76% IoU and 47% object-F1 on FTW, an increase of 6% and 9% over the previous baseline. Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference. We release all models and model-derived field boundary datasets for five countries.

## Semantic Prism: Generative Segmentation with an Explicit Semantic-Image Interface

DevFeed: [Semantic Prism: Generative Segmentation with an Explicit Semantic-Image Interface](<https://devfeed.tech/articles/semantic-prism-generative-segmentation-with-an-explicit-semantic-image-interface-139802.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.11537>)

Author: Weize Cai, Yongqi Dong, Zhida Shao, Zixin Fu, Xiaoxi Hu

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [c](<https://devfeed.tech/tags/c.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [class](<https://devfeed.tech/tags/class.md>), [color](<https://devfeed.tech/tags/color.md>), [combines](<https://devfeed.tech/tags/combines.md>), [condition](<https://devfeed.tech/tags/condition.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [context](<https://devfeed.tech/tags/context.md>), [crop](<https://devfeed.tech/tags/crop.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [define](<https://devfeed.tech/tags/define.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [generative](<https://devfeed.tech/tags/generative.md>), [image](<https://devfeed.tech/tags/image.md>), [interface](<https://devfeed.tech/tags/interface.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

Semantic Prism improves road-scene segmentation by refining the class logits decoded from a generated semantic RGB image. A generator adapted from a diffusion-distilled backbone produces that image in one denoising update per crop; distances to a fixed class-color codebook yield interface logits and pixel probabilities. Hierarchical Generator Evidence Alignment (HGEA) uses aligned multilevel VAE features alongside the input, generated image, and probabilities to correct the logits. On Cityscapes' 500-image validation set, it reaches 72.07% mean mIoU, 11.39 points above direct-interface decoding; capacity-matched ablations favor multilevel refinement over flat or single-level alternatives. The Cityscapes-trained model gets 46.89% mIoU on ACDC without target-domain adaptation, while a separately trained BDD100K model gets 62.22% on its 1,000-image validation set. Contextual Interface Hierarchy Disagreement (C-IHD) ranks pixel errors without an extra network pass; across three datasets it improves AUPR over maximum-softmax uncertainty with predictions fixed. On ACDC, AUPR rises from 0.6580 to 0.7557.

### Source excerpt

arXiv:2608.11537v2 Announce Type: replace-cross Abstract: Conditional image generators can render segmentation maps as semantic RGB images, but color drift and boundary mixing can undermine direct decoding. We present Semantic Prism, a framework that combines an explicit semantic-image interface with hierarchical refinement for road-scene segmentation. A generator adapted from a diffusion-distilled backbone produces a semantic RGB image with a single denoising update per crop. Distances to a fixed class-color codebook define interface logits and pixelwise class probabilities. Hierarchical Generator Evidence Alignment (HGEA) combines spatially aligned multilevel features from the VAE encoder of the generator with the input image, generated semantic image, and interface probabilities to predict additive corrections to these logits. Contextual Interface Hierarchy Disagreement (C-IHD) combines pointwise uncertainty, local context, and interface-refinement disagreement in a fixed score for ranking pixel errors, without an auxiliary predictor or an additional network pass. On the 500-image Cityscapes validation set, Semantic Prism achieves 72.07% mean mIoU, improving on direct-interface decoding by 11.39 percentage points. Extensive capacity-matched ablations show higher mean mIoU for multilevel refinement than for flat and single-level alternatives. The Cityscapes-trained model transfers to ACDC Dataset, achieving 46.89% mIoU without target-domain adaptation. Beyond Cityscapes, on BDD100K dataset, a separately trained model achieves 62.22% mIoU on its full 1,000-image validation set. Across the 3 evaluated datasets, C-IHD improves pixel-error area under the AUPR over uncertainty derived from maximum softmax probability, with segmentation predictions held fixed for each comparison. In particular, on ACDC, AUPR increases from 0.6580 to 0.7557, demonstrating that Semantic Prism presents more effective error ranking under adverse-condition domain shift.

## Smooth Inliers, Erratic Outliers: Frequency-Aware Mamba for Two-View Correspondence Learning

DevFeed: [Smooth Inliers, Erratic Outliers: Frequency-Aware Mamba for Two-View Correspondence Learning](<https://devfeed.tech/articles/smooth-inliers-erratic-outliers-frequency-aware-mamba-for-two-view-correspondence-learning-139777.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.04493>)

Author: Zhihua Wang, Yifeng Gao, Yunhao Feng, Rui Pan, Zhouyuan Ma, Baiheng Zhao, Zixing Chen, Yanping Li, Yizhang Liu, Xingjun Ma

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [outlier-detection](<https://devfeed.tech/topics/outlier-detection.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [camera](<https://devfeed.tech/tags/camera.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [domain](<https://devfeed.tech/tags/domain.md>), [filter](<https://devfeed.tech/tags/filter.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [learning](<https://devfeed.tech/tags/learning.md>), [mamba](<https://devfeed.tech/tags/mamba.md>), [outliers](<https://devfeed.tech/tags/outliers.md>), [pruning](<https://devfeed.tech/tags/pruning.md>), [sequence](<https://devfeed.tech/tags/sequence.md>)

### AI overview

SFMambaNet uses cluster-by-cluster scanning and learnable frequency-domain gates between forward and backward passes to distinguish smoothly varying inlier correspondences from erratic outliers. The abstract reports that, with about two million parameters, it outperforms spatial-domain Mamba baselines on camera pose estimation, outlier removal, and homography estimation. A parameter-free low-pass filter also beats point-wise layers as large as the gates; the learned gates themselves adopt low-pass behavior and make scanning less sensitive to match shuffling. These findings are reported for the described tasks, with broader relevance to unordered-set sequence models proposed by the authors.

### Source excerpt

arXiv:2606.04493v2 Announce Type: replace-cross Abstract: When shown matches between two photographs of the same cathedral, people can tell at a glance which ones are wrong: a window matched to its look-alike jumps against its neighbors, while correct matches shift together. Two-view correspondence learning, also called correspondence pruning, asks a network to make this judgment for thousands of candidate matches, most of which are wrong. Mamba, a fast sequence model, now drives strong pruners, but it reads the matches as a plain sequence, and whether its scan can capture such agreement is unclear. We propose SFMambaNet, which scans the matches cluster by cluster, so that correct matches vary slowly along the sequence while wrong ones stay erratic, and filters the scanned features with learnable frequency-domain gates between its forward and backward passes. On camera pose estimation, outlier removal and homography estimation, we find that SFMambaNet outperforms spatial-domain Mamba baselines with about two million parameters. Contrary to the usual expectation that such gains come from extra capacity, we find that a parameter-free low-pass filter beats point-wise layers as large as the gates. The learned gates turn low-pass on their own and make the scan far less sensitive to how the matches are shuffled. Together, these results show that frequency is a natural language for describing agreement between correspondences, with implications for other sequence models that must read unordered sets, such as point clouds and graphs.

[Next page](<https://devfeed.tech/topics/image-processing.md?cursor=WyIyMDI2LTExLTE4VDA1OjAwOjAwKzAwOjAwIiwgIjEyMmI5NWNmLTA5ODUtNGUzNS1iY2U0LTQ5NzFlMTc4NWY3OCJd>)