# 3D rendering

3D rendering is the process of converting a three-dimensional scene representation into a two-dimensional frame, commonly using graphics hardware and rendering pipelines.

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

## ASUS ProArt GR1X Review: RTX Spark N1X With Two M.2 2280 Slots in 1.15 Liters

DevFeed: [ASUS ProArt GR1X Review: RTX Spark N1X With Two M.2 2280 Slots in 1.15 Liters](<https://devfeed.tech/articles/asus-proart-gr1x-review-rtx-spark-n1x-with-two-m-2-2280-slots-in-1-15-liters-141148.md>)

Original publisher: [Read original article](<https://www.storagereview.com/review/asus-proart-gr1x-review>)

Author: Dylan Bryan

Published: 2026-11-18T14:40:41Z

Content type: article

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [ASUS](<https://devfeed.tech/topics/asus.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>), [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Windows](<https://devfeed.tech/topics/windows.md>), [M.2 NVMe](<https://devfeed.tech/topics/m-2-nvme.md>), [NVMe](<https://devfeed.tech/topics/nvme.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [10gbe](<https://devfeed.tech/tags/10gbe.md>), [2](<https://devfeed.tech/tags/2.md>), [asus](<https://devfeed.tech/tags/asus.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cooler](<https://devfeed.tech/tags/cooler.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [end-user](<https://devfeed.tech/tags/end-user.md>), [fan](<https://devfeed.tech/tags/fan.md>), [first](<https://devfeed.tech/tags/first.md>), [m-2](<https://devfeed.tech/tags/m-2.md>), [msi](<https://devfeed.tech/tags/msi.md>), [n1x](<https://devfeed.tech/tags/n1x.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [pcie](<https://devfeed.tech/tags/pcie.md>), [pro](<https://devfeed.tech/tags/pro.md>), [review](<https://devfeed.tech/tags/review.md>), [rtx](<https://devfeed.tech/tags/rtx.md>), [rtx-spark](<https://devfeed.tech/tags/rtx-spark.md>), [spark](<https://devfeed.tech/tags/spark.md>), [square](<https://devfeed.tech/tags/square.md>), [with](<https://devfeed.tech/tags/with.md>), [workstation](<https://devfeed.tech/tags/workstation.md>)

### AI overview

The ASUS ProArt GR1X's main advantage is cooling: in the review's 30-minute Cinebench loop it sustained 7,306 points, 5-12% ahead of the tested RTX Spark laptops, while averaging 83.3°C versus their 97°C. It also outperformed them by 18-25% when serving eight concurrent requests to a 27B model. Against MSI's EdgeMesa mini PC, performance was generally within 2%, though the GR1X ran cooler in CPU tests and offers two M.2 2280 slots. The tested 64GB model handled workloads through the 27B class, but not the 35B coding-agent tier or Qwen-Image at Q8; larger models require choosing the 128GB configuration at purchase. Its included 1TB Gen4 SSD was a weak point for cold model loads (10.94 seconds for a 12.8GB model, versus 7.00 seconds on the EdgeMesa's Gen5 drive), but the second slot accepts a standard retail SSD. The review frames the GR1X as a compact Windows desktop whose sustained output and storage expandability come with limited front connectivity and no built-in display or keyboard.

### Source excerpt

The ASUS ProArt GR1X packs NVIDIA's RTX Spark N1X into a 150mm-square, 1.15-liter desktop with two M.2 2280 SSD slots, 10GbE, and a dual-fan cooler ASUS built to sustain 140W. Our review unit is the 64GB configuration with a 1TB PCIe Gen4 SSD and Windows 11 Pro. We tested it alongside MSI's 128GB EdgeMesa N The post ASUS ProArt GR1X Review: RTX Spark N1X With Two M.2 2280 Slots in 1.15 Liters appeared first on StorageReview.com.

## A Gaussian Primitive Data Management Framework for Efficient 3DGS Trajectory Rendering

DevFeed: [A Gaussian Primitive Data Management Framework for Efficient 3DGS Trajectory Rendering](<https://devfeed.tech/articles/a-gaussian-primitive-data-management-framework-for-efficient-3dgs-trajectory-rendering-138299.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20546>)

Author: Haolun Ma, Ziyi Liu, Zizhuo Xu, Chuhan Hu, Lei Li

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>)

Tags: [3dgs](<https://devfeed.tech/tags/3dgs.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [framework](<https://devfeed.tech/tags/framework.md>), [latency](<https://devfeed.tech/tags/latency.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [spatial-data](<https://devfeed.tech/tags/spatial-data.md>)

### AI overview

GDM-GS targets redundant work in trajectory rendering with Structured 3D Gaussian Splatting (3DGS), where each view projects all anchors, may decode anchors already needed by neighboring views, and runs GPU steps while the CPU idles. It treats views as spatial range queries and decoded Gaussians as shared derived data. Within each view, anchor and occluder indexes form a holed-frustum query to avoid decoding out-of-view or provably hidden anchors. Across consecutive views, shared materialization decodes each requested anchor once per group while preserving per-view selection. A hybrid pipeline balances selection between CPU and GPU before grouped decoding under bounded memory. Experiments on large-scale public scenes reportedly reduce trajectory-rendering latency substantially while preserving image quality; the excerpt gives no quantitative results.

### Source excerpt

arXiv:2611.20546v1 Announce Type: new Abstract: Trajectory rendering, which renders novel views of a reconstructed 3D scene along a camera path, is a core operation in digital twins and autonomous inspection. Structured 3D Gaussian Splatting (3DGS) renders a single view in real time by decoding sparse anchors into Gaussians on demand, but it renders a trajectory view by view: every view projects all anchors to select them, re-decodes anchors already requested by neighboring views, and runs all steps on the GPU while the CPU idles. We treat this as a spatial data management problem, where anchors are spatial objects, views are range queries, and decoded Gaussians are shared derived data, and propose GDM-GS, which removes redundancy at three levels. Within a view, an anchor index and an occluder index answer each view as a holed-frustum range query, so out-of-view and provably hidden anchors are never decoded. Across views, shared materialization decodes each requested anchor once per group of consecutive views while preserving each view's selection. Across processors, a hybrid pipeline balances selections between the CPU and the GPU before grouped decoding under bounded memory. Experiments on large-scale public scenes show that GDM-GS substantially reduces trajectory rendering latency while preserving image quality.

## VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender

DevFeed: [VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender](<https://devfeed.tech/articles/vibeprevisbench-evaluating-agentic-coding-for-4d-scene-generation-in-blender-132172.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15789>)

Author: Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, Jiankang Chen, Kaiyu Jiang, Haoyu Zhang, Hongyi Fu, Jianxiong Wang, Tianke Zhang, Haonan Fan, Yingxin Li, Bingyi Li, Xu W

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [blender](<https://devfeed.tech/topics/blender.md>), [3D](<https://devfeed.tech/topics/3d.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [basic](<https://devfeed.tech/tags/basic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [better](<https://devfeed.tech/tags/better.md>), [blender](<https://devfeed.tech/tags/blender.md>), [build](<https://devfeed.tech/tags/build.md>), [but](<https://devfeed.tech/tags/but.md>), [camera](<https://devfeed.tech/tags/camera.md>), [can](<https://devfeed.tech/tags/can.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [generation](<https://devfeed.tech/tags/generation.md>), [scene-generation](<https://devfeed.tech/tags/scene-generation.md>)

### AI overview

VibePrevisBench evaluates whether coding agents can turn a brief into an executable Blender 4D scene and rendered graybox proxy video. Its 242 tasks cover four input types, including scripts, photos, continuations, and reference videos. It scores each delivery with a rule-based Scene Check that reruns code and compares exported scenes with hidden facts across nine dimensions, and a VLM-based Screen Check that tests whether passed facts are recognizable in the video. Analysis of 11 frontier agents finds multimodal understanding--especially of space and camera motion--distinguishes performance; basic camera work and staging appear mastered, while challenging requests remain difficult. Agents inspect renders but often fail to correct errors, pointing to needs for stronger spatial and camera understanding, explicit checks for difficult requirements, and item-by-item render verification against the brief.

### Source excerpt

arXiv:2611.15789v1 Announce Type: cross Abstract: Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene in Blender, yet no benchmark checks both these videos and the long, multi-shot scenes behind them. We introduce VibePrevisBench, a benchmark for 4D scene reconstruction: an agent turns a brief into an executable 4D scene and renders its proxy video. Its 242 tasks span four input kinds, including scripts, photos, continuations, and reference videos. Each delivery is scored along two evaluation dimensions. Rule-based Scene Check re-runs the code and compares the exported 4D scene with hidden ground truth facts in nine dimensions. VLM-based Screen Check asks a VLM judge whether the facts that pass can be recognized in the proxy video. We analyze the evaluation results and trajectories of 11 frontier coding agents and identify three key observations. First, multimodal understanding separates the agents, especially in understanding space and camera motion. Second, all agents seem to already master basic camera work and staging, and fail at challenging requests. Third, agents inspect their own renders but fail to correct their errors. Agents thus need better visual understanding of space and camera, explicit checks for challenging requests, and item-by-item verification of renders against the brief.

## Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation

DevFeed: [Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation](<https://devfeed.tech/articles/instant-nurec-feed-forward-3d-gaussian-reconstruction-for-driving-scene-simulation-131951.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.14203>)

Author: NVIDIA, :, Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang, Seung Wook Kim, Ning Xu, Qi Wu, Janick Martinez Esturo, Shengyu Huang, Nick Schneider, Laura Leal-Ta

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3dgs](<https://devfeed.tech/tags/3dgs.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [camera](<https://devfeed.tech/tags/camera.md>), [central](<https://devfeed.tech/tags/central.md>), [costs](<https://devfeed.tech/tags/costs.md>), [critical](<https://devfeed.tech/tags/critical.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>), [dataset](<https://devfeed.tech/tags/dataset.md>), [development](<https://devfeed.tech/tags/development.md>), [driving](<https://devfeed.tech/tags/driving.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [gaussian-splatting](<https://devfeed.tech/tags/gaussian-splatting.md>), [instant](<https://devfeed.tech/tags/instant.md>), [simulation](<https://devfeed.tech/tags/simulation.md>)

### AI overview

Instant NuRec converts a short, calibrated multi-camera driving log into a simulatable 3D Gaussian Splatting scene in one forward pass, avoiding the per-scene tuning and slower reconstruction described for existing neural simulation methods. It outputs separate static and dynamic 3DGS layers, a sky cubemap, and per-camera ISP corrections, and supports non-pinhole cameras through 3DGUT. The abstract reports reconstructing a 10-20-second scene in about 1.5 seconds and a Waymo Open Dataset PSNR 2.01 dB above the strongest evaluated baseline. It is integrated with NuRec and compatible with AlpaSim for closed-loop simulation.

### Source excerpt

arXiv:2607.14203v2 Announce Type: replace-cross Abstract: 3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent years, neural simulation has become predominant, with methods such as NuRec playing a central role; however, these methods remain relatively slow and typically require per-scene tuning. In this work, we present Instant NuRec, a feed-forward neural reconstruction model that turns a short multi-view driving log into a fully simulatable 3D Gaussian Splatting (3DGS) world in a single forward pass. The model accepts multi-view input from a calibrated camera rig and emits a layered output consisting of static and dynamic 3DGS layers, a sky cubemap, and per-camera ISP corrections, while providing native support for non-pinhole camera models via 3DGUT. It reconstructs a 10-20-second multi-camera scene in roughly 1.5 seconds and achieves a PSNR on the Waymo Open Dataset that is 2.01 dB above the strongest evaluated baseline. Instant NuRec is deeply integrated into NuRec and is compatible with AlpaSim for closed-loop simulation.

## llm-gemini 0.36

DevFeed: [llm-gemini 0.36](<https://devfeed.tech/articles/llm-gemini-0-36-127727.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/10/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-10T20:09:44Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [3D](<https://devfeed.tech/topics/3d.md>), [browser-game](<https://devfeed.tech/topics/browser-game.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-317](<https://devfeed.tech/tags/ai-2-317.md>), [animation](<https://devfeed.tech/tags/animation.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [blender](<https://devfeed.tech/tags/blender.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-game](<https://devfeed.tech/tags/browser-game.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-201](<https://devfeed.tech/tags/gemini-201.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-056](<https://devfeed.tech/tags/generative-ai-2-056.md>), [google](<https://devfeed.tech/tags/google.md>), [google-419](<https://devfeed.tech/tags/google-419.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6-1](<https://devfeed.tech/tags/gpt-6-1.md>), [gpt-6-1-sol](<https://devfeed.tech/tags/gpt-6-1-sol.md>), [js](<https://devfeed.tech/tags/js.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-649](<https://devfeed.tech/tags/llm-649.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-241](<https://devfeed.tech/tags/llm-release-241.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-020](<https://devfeed.tech/tags/llms-2-020.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [medium](<https://devfeed.tech/tags/medium.md>), [model](<https://devfeed.tech/tags/model.md>), [music](<https://devfeed.tech/tags/music.md>), [nano](<https://devfeed.tech/tags/nano.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-157](<https://devfeed.tech/tags/pelican-riding-a-bicycle-157.md>), [yonkers-rising](<https://devfeed.tech/tags/yonkers-rising.md>)

### AI overview

Gemini 4 Carbon became generally available after an initial release to a subset of cyber defenders. The excerpt reports launch pricing of $2 per million input tokens and $10 per million output tokens, scheduled to rise to $4 and $20 on December 1. Thinking effort has low, medium, and high settings, with medium as the default. In Google's Antigravity IDE, a prompt produced a Three.js animation of a mech stomping through New York; a follow-up prompt was needed to make the HTML standalone without external dependencies. A separate video description reports an Antigravity /swarm project that coordinated subagents to build a Three.js campus exploration game with Blender assets, WebGL shaders, Web Audio effects, and Lyria music. These are examples, not a comparative evaluation.

### Source excerpt

Release: llm-gemini 0.36 Gemini 4 Carbon was announced two weeks ago for "a subset of cyber defenders", but today it's available to everyone else. This is Google's best ever Gemini, priced at $2/million input and $10/million output at launch (that's GPT-6.1 Sol / Claude Sonnet 5.5 prices) but scheduled to double in price to $4/$20 on December 1st (same as Opus 5.5). Here are three pelicans for the low, medium and high thinking efforts (it defaults to medium). This is the pelican I got for high: Gemini pelicans have all been great for a while now, so I also tested it out using Google's Antigravity IDE with a prompt I first tried with Claude Fable 5.2 yesterday: Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's the HTML result (I had to prompt "build that into a standalone HTML file" to get a version with no external dependencies). I then screen-captured that as a video: Update: Huh, just saw this on YouTube: Using Google Antigravity's /swarm feature, Carbon built an open-world 3D game where you explore Google's Mountain View campus as a pelican riding a GBike -- coordinating subagents to model 3D assets in Blender from Omni and Nano Banana references, build the browser game in Three.js with WebGL shaders, and pair procedural Web Audio sound effects with Lyria music. Tags: llm-release, gemini, llm, google, generative-ai, ai, llms, pelican-riding-a-bicycle

## A four-view smartphone video dataset of a robot-held flexible strip, with camera poses and a 3D LaGSplat baseline

DevFeed: [A four-view smartphone video dataset of a robot-held flexible strip, with camera poses and a 3D LaGSplat baseline](<https://devfeed.tech/articles/a-four-view-smartphone-video-dataset-of-a-robot-held-flexible-strip-with-camera-poses-and-a-3d-lagsplat-baseline-125116.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09959>)

Author: Louen Pottier

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [acceleration](<https://devfeed.tech/tags/acceleration.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [browser](<https://devfeed.tech/tags/browser.md>), [camera](<https://devfeed.tech/tags/camera.md>), [cameras](<https://devfeed.tech/tags/cameras.md>), [code](<https://devfeed.tech/tags/code.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>), [dataset](<https://devfeed.tech/tags/dataset.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [demo](<https://devfeed.tech/tags/demo.md>), [film](<https://devfeed.tech/tags/film.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [robot](<https://devfeed.tech/tags/robot.md>), [smartphone](<https://devfeed.tech/tags/smartphone.md>), [video](<https://devfeed.tech/tags/video.md>), [view](<https://devfeed.tech/tags/view.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The note presents synchronized four-view smartphone footage of a robot-driven flexible strip, with camera poses and per-frame gripper position as the measured input. Three iPhones are fixed and one is handheld; recording lasts ten minutes. It applies LaGSplat, whose video-learned latent state serves both as the generalized coordinate of a dissipative Lagrangian and as input to a Gaussian Splatting decoder. Using gripper acceleration as a forcing term, the model renders held-out views at 26-33 dB PSNR and supports a real-time browser demo. The dataset, checkpoints, and training code are public.

### Source excerpt

arXiv:2611.09959v1 Announce Type: cross Abstract: This note describes a multi-view video dataset of a deformable object driven by a measured input, with the measured pose of every camera, and a first 3D result obtained on it with LaGSplat. LaGSplat learns from video a low-dimensional latent state that is both the generalized coordinate of a learned dissipative Lagrangian and the conditioning variable of a Gaussian Splatting decoder; fitting the decoder in 3D calls for synchronized multi-view footage, which the original paper only had from synthetic renderings. Here a robot arm moves a flexible strip by oscillating along a one-dimensional path, and four iPhones, three fixed and one handheld, film it for ten minutes. The videos are synchronized, the cameras are posed from the scene, and the position of the gripper is given per frame as the input of the system. LaGSplat fitted on this data with the gripper acceleration as a forcing term renders held-out views at 26 to 33 dB PSNR and runs as a real-time interactive demo in a web browser. Dataset, checkpoints and training code are public.

## Mitigating SM-Level Load Imbalance in 3D Gaussian Splatting on GPUs

DevFeed: [Mitigating SM-Level Load Imbalance in 3D Gaussian Splatting on GPUs](<https://devfeed.tech/articles/mitigating-sm-level-load-imbalance-in-3d-gaussian-splatting-on-gpus-125543.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12319>)

Author: Junha Ryu, Hoi-Jun Yoo

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>)

Tags: [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3dgs](<https://devfeed.tech/tags/3dgs.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [blending](<https://devfeed.tech/tags/blending.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [gpu-scheduling](<https://devfeed.tech/tags/gpu-scheduling.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [load](<https://devfeed.tech/tags/load.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [outlier](<https://devfeed.tech/tags/outlier.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [schedule](<https://devfeed.tech/tags/schedule.md>), [sm](<https://devfeed.tech/tags/sm.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [world-models](<https://devfeed.tech/tags/world-models.md>)

### AI overview

Uneven work across screen tiles creates a long execution tail in GPU-based 3D Gaussian Splatting: a few SMs process heavy tiles while most sit idle, especially in large urban scenes. The proposed software scheduling approach uses a persistent kernel to prioritize heavy tiles and selectively splits outlier tiles across multiple CTAs. A per-frame policy uses tile statistics already available in the rendering pipeline to decide when and how much to split. The method requires neither retraining nor specialized hardware, preserves the original alpha blending formulation, and is described as compatible with existing optimizations across 3DGS variants. The abstract reports up to 2.93x average per-scene acceleration for alpha blending on a large urban scene and up to 5.6x on its most imbalanced frames.

### Source excerpt

arXiv:2611.12319v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) enables photorealistic, real-time rendering on commodity GPUs and is increasingly adopted in generative world models and autonomous driving simulators. However, existing optimizations rely on algorithmic changes that often require retraining, or on specialized accelerators that lack flexibility across evolving 3DGS variants. In this paper, we identify a fundamental inefficiency in GPU-based 3DGS rendering: severe SM-level load imbalance caused by uneven workloads across screen tiles. This imbalance creates a long execution tail, leaving most SMs idle while a few process computationally intensive tiles, particularly in large-scale urban scenes. To address this, we present a software-defined GPU scheduling approach that mitigates the execution tail. Our approach uses a persistent kernel to schedule heavy tiles first and selectively chunks outlier tiles across multiple CTAs. A lightweight per-frame policy determines when and how much to chunk using tile statistics already available in the rendering pipeline. Our approach requires neither retraining nor specialized hardware and can be applied orthogonally to existing optimizations across diverse 3DGS variants. Averaged per scene, it accelerates alpha blending by up to 2.93x on a large-scale urban scene, and by up to 5.6x on its most imbalanced frames, while retaining the original alpha blending formulation.

## LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding

DevFeed: [LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding](<https://devfeed.tech/articles/lsd-3d-large-scale-3d-driving-scene-generation-with-geometry-grounding-119979.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2508.19204>)

Author: Julian Ost, Andrea Ramazzina, Amogh Joshi, Maximilian B\\"omer, Mario Bijelic, Felix Heide

Published: 2026-11-06T05:00:00Z

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>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [allows](<https://devfeed.tech/tags/allows.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [can](<https://devfeed.tech/tags/can.md>), [causality](<https://devfeed.tech/tags/causality.md>), [combines](<https://devfeed.tech/tags/combines.md>), [complex](<https://devfeed.tech/tags/complex.md>), [control](<https://devfeed.tech/tags/control.md>), [cost](<https://devfeed.tech/tags/cost.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>), [driving](<https://devfeed.tech/tags/driving.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [large](<https://devfeed.tech/tags/large.md>), [scale](<https://devfeed.tech/tags/scale.md>), [scene-generation](<https://devfeed.tech/tags/scene-generation.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

LSD-3D generates controllable, geometry-grounded 3D driving scenes to address limits of both reconstruction from captured data and image or video diffusion. It combines a proxy geometry and environment representation with score distillation from learned 2D image priors. According to the abstract, scenes can be prompt-guided and conditioned on map layouts, with explicit 3D geometry estimation and causal novel-view synthesis that preserves object permanence. The authors report realistic, geometrically consistent scenes with high-fidelity texture and structure; the excerpt does not provide quantitative evaluation details.

### Source excerpt

arXiv:2508.19204v2 Announce Type: replace-cross Abstract: Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these methods have baked-in static environments and only allow for limited scene control -- they are functionally constrained in scene and trajectory diversity by the captures from which they are reconstructed. In contrast, generating driving data with recent image or video diffusion models offers control, however, at the cost of geometry grounding and causality. In this work, we aim to bridge this gap and present a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal novel view synthesis with object permanence and explicit 3D geometry estimation. The proposed method combines the generation of a proxy geometry and environment representation with score distillation from learned 2D image priors. We find that this approach allows for high controllability, enabling the prompt-guided geometry and high-fidelity texture and structure that can be conditioned on map layouts -- producing realistic and geometrically consistent 3D generations of complex driving scenes.

## 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering

DevFeed: [4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering](<https://devfeed.tech/articles/4d-point-splatting-for-mmwave-radar-micro-doppler-differentiable-rendering-120733.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08342>)

Author: Adnan Armouti, Guanyue Qian, Rajalakshmi Nandakumar

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

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

Topics: [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [GPU rendering](<https://devfeed.tech/topics/gpu-rendering.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [3D](<https://devfeed.tech/topics/3d.md>), [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>)

Tags: [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [doppler](<https://devfeed.tech/tags/doppler.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [features](<https://devfeed.tech/tags/features.md>), [gap](<https://devfeed.tech/tags/gap.md>), [generation](<https://devfeed.tech/tags/generation.md>), [mmwave](<https://devfeed.tech/tags/mmwave.md>), [point](<https://devfeed.tech/tags/point.md>), [radar](<https://devfeed.tech/tags/radar.md>), [range](<https://devfeed.tech/tags/range.md>), [raw](<https://devfeed.tech/tags/raw.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [signal-processing](<https://devfeed.tech/tags/signal-processing.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

4D Point Splatting (4DPS) fits an explicit moving scene to real mmWave radar captures, aiming to narrow the sim2real gap that forward simulators, learned generators, and static-scene inverse renderers do not address. It initializes room and body geometry from synchronized camera data, represents the scene as oriented points with material, normal, and velocity, and splats them into range and Doppler bins to produce raw complex radar returns. The same signal processing can then create representations for downstream models. Fitting 235 HuPR sequences and 100 RT-Pose sequences yielded median correlations of 0.940/0.830 for range-azimuth, 0.829/0.695 for range-Doppler, and 0.988/0.966 for micro-Doppler. On RT-Pose, a pose model trained on 4DPS renders achieved 21.9 cm MPJPE on real data, compared with 16.7 cm for real-data training and 127.6 cm for the RF-Genesis baseline. A sequence fit took 5.7 minutes on HuPR and 12.9 minutes on RT-Pose using one H100.

### Source excerpt

arXiv:2611.08342v1 Announce Type: cross Abstract: Millimeter-wave radar resolves the micrometer displacements of a moving body as micro-Doppler, enabling gait, gesture, activity, pose and vital-sign sensing. Each task relies on a downstream model trained on real data, yet radar datasets lag orders of magnitude behind vision and language. Brute-force collection will not close that gap, and existing synthesis methods (forward-only simulators, learned generators and static-scene inverse renderers) cannot fit a real capture of a moving body, leaving a sim2real gap. We present 4D Point Splatting (4DPS), a physics-based differentiable renderer that fits an explicit moving scene to a real capture. Using the synchronized camera to initialize the room and body, we represent the scene as oriented points carrying material, normal and velocity, and splat each point into range and Doppler bins. Our output is the raw complex return a real radar records, so we apply the same signal processing on the rendered data to obtain any representation for training any SOTA downstream model. We fit 235 sequences on HuPR and 100 on RT-Pose, two datasets with different radars. Our reconstructions set the state of the art, with median correlations of 0.940 and 0.830 on range-azimuth, 0.829 and 0.695 on range-Doppler, and 0.988 and 0.966 on micro-Doppler. Our renders also set the state of the art in downstream sim2real gap. On RT-Pose, a pose model trained on them reaches 21.9 cm MPJPE on real data, against 16.7 cm for real training and 127.6 cm for the RF-Genesis baseline, where both the rendered- and real-trained models learn nearly the same features. Our custom CUDA kernels fit a sequence in 5.7 minutes on HuPR and 12.9 on RT-Pose on one H100, making dataset-scale inverse rendering of mmWave radar possible for the first time. This work can enable synthetic data generation for any human-centered downstream task and model, and scene editing for data augmentation.

## Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification

DevFeed: [Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification](<https://devfeed.tech/articles/quo-vadis-driving-scene-reconstruction-occlusion-aware-gaussian-densification-118441.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06273>)

Author: Dung Do Tien, Kien Nguyen Do Trung, Kiet Dang Vu, Trung Thai Tran, Duc Dung Nguyen

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [completion](<https://devfeed.tech/tags/completion.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [driving](<https://devfeed.tech/tags/driving.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [novel](<https://devfeed.tech/tags/novel.md>)

### AI overview

OccSplat addresses incomplete driving-scene reconstructions by adding predicted 3D Gaussian primitives where input views leave occluded regions unsupported, instead of filling missing pixels in rendered images. Its Gaussian Occlusion Mapping identifies those regions, and Gaussian Occlusion Completion generates primitives that are integrated into the original representation. The feed-forward method requires no per-scene optimization. On nuScenes, it improves on the compared methods, with particularly large gains in occluded regions; the supplied excerpt gives no numerical results.

### Source excerpt

arXiv:2611.06273v1 Announce Type: cross Abstract: While recent feed-forward 3D Gaussian Splatting methods enable efficient driving-scene reconstruction from surround-view images, their reliance on a single observation fundamentally hinders novel-view synthesis. Regions occluded in the input can become visible from novel viewpoints, leaving the reconstructed Gaussians under-constrained and incomplete. Moving beyond image-space inpainting for rendered views, we introduce OccSplat, a feed-forward framework whose core contribution is Occlusion-Aware Gaussian Densification, explicitly targeting missing scene geometry rather than missing pixels. By predicting new Gaussian primitives for unsupported regions, OccSplat completes the scene directly in the 3D representation. Specifically, OccSplat first identifies occluded regions that lack Gaussian support through Gaussian Occlusion Mapping. Gaussian Occlusion Completion then generates new primitives for these regions. The predicted primitives are integrated into the original representation to improve novel-view synthesis while retaining feed-forward inference without per-scene optimization. Experiments on the nuScenes benchmark demonstrate that OccSplat improves on the compared methods and yields particularly large gains in occluded regions, leading to more accurate and visually coherent driving-scene reconstruction.

## Investigating Anthropometric Fidelity in SAM 3D Body

DevFeed: [Investigating Anthropometric Fidelity in SAM 3D Body](<https://devfeed.tech/articles/investigating-anthropometric-fidelity-in-sam-3d-body-118187.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2601.06035>)

Author: Aizierjiang Aiersilan, Ruting Cheng, James Hahn

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

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

Topics: [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Image](<https://devfeed.tech/topics/image.md>), [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [body](<https://devfeed.tech/tags/body.md>), [but](<https://devfeed.tech/tags/but.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [coherent](<https://devfeed.tech/tags/coherent.md>), [combined](<https://devfeed.tech/tags/combined.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [details](<https://devfeed.tech/tags/details.md>), [development](<https://devfeed.tech/tags/development.md>), [domain](<https://devfeed.tech/tags/domain.md>), [effect](<https://devfeed.tech/tags/effect.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [extend](<https://devfeed.tech/tags/extend.md>), [sam](<https://devfeed.tech/tags/sam.md>)

### AI overview

SAM 3D Body produces clean, coherent meshes from single images and handles occlusion and varied poses, but the abstract reports that it smooths over distinctive body features, including geriatric muscle atrophy, scoliosis, and pregnancy. The authors attribute this regression toward average anatomy to the low-dimensional Momentum Human Rig representation, DINOv3 semantic-invariant conditioning, and annotation-based alignment--a perception-distortion trade-off rather than a lack of model capacity. They propose implicit-explicit hybrid representations and Medical-in-the-Loop alignment as directions for improving fidelity in high-precision medical applications.

### Source excerpt

arXiv:2601.06035v2 Announce Type: cross Abstract: The release of SAM 3D Body is a recent development in human mesh recovery, demonstrating improved performance in producing clean, topologically coherent meshes from single images. By leveraging the Momentum Human Rig (MHR), it achieves robustness to occlusion and diverse poses. However, our evaluation reveals a specific and consistent limitation: the model struggles to reconstruct detailed anthropometric deviations, particularly in populations exhibiting distinctive morphological alterations such as geriatric muscle atrophy, scoliosis, or pregnancy, even when these features are prominent in the input image. In this paper, we investigate this phenomenon not as a failure of the model's capacity, but as a byproduct of the "perception-distortion trade-off". We posit that the architectural reliance on the low-dimensional parametric MHR representation, combined with semantic-invariant conditioning (DINOv3) and annotation-based alignment, creates a pervasive "regression to the mean" effect. We analyze these mechanisms to understand why individual biological details are smoothed out. Furthermore, we state our contributions by proposing specific, constructive pathways for future work, such as implicit-explicit hybrid representations and Medical-in-the-Loop alignment, to extend the baseline performance of SAM 3D Body into the high-precision medical domain.

## Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation

DevFeed: [Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation](<https://devfeed.tech/articles/hybrid-particle-voxel-dynamics-for-multimodal-3d-world-simulation-116947.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04492>)

Author: Jimmy Wang, Yifan Chou, Kaifeng Zhang, Yixuan Wang, Binghao Huang, Tao Yu, Saleh Nabi, Yunzhu Li

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

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

Topics: [World models](<https://devfeed.tech/topics/world-models.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D visualization](<https://devfeed.tech/topics/3d-visualization.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [actions](<https://devfeed.tech/tags/actions.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [camera](<https://devfeed.tech/tags/camera.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [voxel](<https://devfeed.tech/tags/voxel.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

3D World Simulator predicts how robot actions change a scene using a shared 3D representation that jointly models appearance, geometry, and tactile observations. A hybrid particle-voxel autoencoder compresses point clouds into voxel latents, and an action-conditioned dynamics model predicts their evolution. The representation enables geometrically consistent rendering from arbitrary viewpoints and integration of spatially aligned tactile signals. The abstract reports interactive long-horizon multimodal prediction at 50 Hz, data generation for policy training and evaluation from tactile and multi-view observations, and model-based planning with unseen objects and robot configurations. These claims are based on the supplied abstract; it provides no comparative performance results.

### Source excerpt

arXiv:2611.04492v1 Announce Type: cross Abstract: Predicting how the world evolves in response to robot actions is central to policy learning, evaluation, and planning. However, many action-conditioned world models predict future observations in 2D image or video space without explicitly modeling the underlying 3D scene, making spatial consistency across viewpoints and over long-horizon interactions challenging. We introduce 3D World Simulator, an action-conditioned multimodal world modeling framework that jointly predicts appearance, geometry, and tactile observations from a unified 3D representation. Our approach combines a hybrid particle-voxel autoencoder that compresses point clouds into compact 3D voxel latents with an action-conditioned latent dynamics model that predicts their evolution. The shared 3D representation supports geometrically consistent rendering from arbitrary viewpoints and flexible integration of spatially aligned tactile signals. Our experiments demonstrate interactive, long-horizon, multimodal prediction at 50 Hz. We then show how our model enables scalable data generation for policy training and evaluation using tactile and multi-view visual observations, including wrist-mounted and novel camera views. Furthermore, we scale our method to large datasets containing diverse objects and demonstrate model-based planning with unseen objects and robot configurations. Together, these results highlight the potential of hybrid particle-voxel dynamics as a foundation for multimodal 3D world simulation.

## Introducing Three-Live: turning AI-generated Three.js into interactive 3D, AR, and WebXR across web and mobile

DevFeed: [Introducing Three-Live: turning AI-generated Three.js into interactive 3D, AR, and WebXR across web and mobile](<https://devfeed.tech/articles/introducing-three-live-turning-ai-generated-three-js-into-interactive-3d-ar-and-webxr-across-web-and-mobile-116355.md>)

Original publisher: [Read original article](<http://opensource.googleblog.com/2026/11/introducing-three-live-ai-generated-3d-ar-webxr.html>)

Author: Google Open Source (noreply@blogger.com)

Published: 2026-11-03T19:30:00Z

Content type: release

Language: en

Sources: [Google Open Source Blog](<https://devfeed.tech/sources/google-open-source-blog.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Three.js](<https://devfeed.tech/topics/threejs.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>), [interactive web graphics](<https://devfeed.tech/topics/interactive-web-graphics.md>), [WebXR](<https://devfeed.tech/topics/webxr.md>), [3D visualization](<https://devfeed.tech/topics/3d-visualization.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-authored](<https://devfeed.tech/tags/ai-authored.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [also](<https://devfeed.tech/tags/also.md>), [android](<https://devfeed.tech/tags/android.md>), [android-xr](<https://devfeed.tech/tags/android-xr.md>), [animations](<https://devfeed.tech/tags/animations.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [api](<https://devfeed.tech/tags/api.md>), [ar](<https://devfeed.tech/tags/ar.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [interactive-3d](<https://devfeed.tech/tags/interactive-3d.md>), [live](<https://devfeed.tech/tags/live.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rust](<https://devfeed.tech/tags/rust.md>), [three-js](<https://devfeed.tech/tags/three-js.md>), [web](<https://devfeed.tech/tags/web.md>), [webxr](<https://devfeed.tech/tags/webxr.md>)

### AI overview

Three-Live is an Apache 2.0 Developer Preview that compiles untrusted Three.js scripts into portable GLB or USDZ scenes for rendering through web, Android, and Apple platform graphics pipelines. The web sandbox removes network APIs before execution; native and command-line builds use the Rust-based Boa compiler. Both impose execution timeouts and geometry quotas. The excerpt reports compilation typically takes 2-5 ms. Web packages provide a custom WebGL2 renderer and AR handoff; Android targets Filament and Scene Viewer, while iOS and macOS target RealityKit and AR Quick Look. Inline client scripts require an explicit opt-in. The viewer-only web build omits scripting and AR handoff. Three-Live is described as an unofficial, simpler companion to the more feature-rich XR Blocks; it is currently a Developer Preview.

### Source excerpt

by Jonathan Bingham, AI Foundations Want to add AI-generated 3D or XR to your web or mobile app? Unsure how to get started? That's why we created the open source cross-platform project Three-Live--written entirely by Google Antigravity, in partnership with one former software engineer turned product manager. (Three-Live is not an officially supported Google product.) You can think of Three-Live as a simple, unofficial companion to the more capable and feature-rich XR Blocks, Android XR's web-based cross-platform framework for XR. The goal of Three-Live is to make it easy to get started with 3D and XR that's AI-authored in Three.js. Three-Live combines the familiar developer experience of <model-viewer> and native mobile libraries with a sandboxed compiler for on-device or server-side compilation of untrusted LLM-generated JavaScript. Large language models (LLMs) have gotten remarkably good at writing software, and that includes generating 3D code in procedural Three.js JavaScript that describes objects, materials, lighting, and animations. But runtime AI-generated code is not trusted, and requires security sandboxing for safe execution. Also, mobile devices provide native support for 3D and XR rendering, and forcing them to run a webview limits the performance. Today, we are excited to release Three-Live (v1.0.0, Developer Preview) under the Apache 2.0 license. It's a lightweight, cross-platform open source library and on-device compiler that bridges the gap between AI-generated Three.js code and high-performance 3D, AR, and WebXR rendering across web, Android, and iOS. How Three-Live works Rather than use Three.js as a browser-only rendering loop, Three-Live treats a declarative subset of the Three.js API as a universal, portable scene description language: Sandboxed execution with strict resource quotas: On the web, untrusted scripts execute inside an isolated Web Worker (with an optional opaque-origin sandboxed <iframe> tier) where network primitives (fetch, XMLHt

## SHield: Watermarking 4D Gaussian Splatting via Spherical Harmonic Coefficient Perturbation

DevFeed: [SHield: Watermarking 4D Gaussian Splatting via Spherical Harmonic Coefficient Perturbation](<https://devfeed.tech/articles/shield-watermarking-4d-gaussian-splatting-via-spherical-harmonic-coefficient-perturbation-114045.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01162>)

Author: Kunal Bhosikar, Prajas Wadekar, Venkata Sai Pranav Bachina, Ankit Gangwal, Charu Sharma, Nicole Meng, Yingjie Lao

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [Image](<https://devfeed.tech/topics/image.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [gaussian-splatting](<https://devfeed.tech/tags/gaussian-splatting.md>), [image](<https://devfeed.tech/tags/image.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [rgb](<https://devfeed.tech/tags/rgb.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [shield](<https://devfeed.tech/tags/shield.md>), [verification](<https://devfeed.tech/tags/verification.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

SHield embeds full-resolution RGB images in 4D Gaussian Splatting files by tiling a zero-mean payload across spherical-harmonic coefficients of a key-selected Gaussian subset, then applying brief anchored optimization to preserve visual fidelity. Ownership verification re-associates the key through canonical Gaussian centres and recovers the payload with deterministic arithmetic, avoiding a neural decoder and rendered-video extraction. Across 30 D-NeRF, HyperNeRF, and DyNeRF scenes, the excerpt reports Pearson recovery of at least 0.991 on 150 models with mean rendering penalty no greater than 0.13 dB; held-out tests had 400 true detections and zero false positives in 1,600 wrong-subset trials. Robustness is bounded: image payloads survive INT8 quantization and 30% opacity pruning, while after aggressive SH-degree-1 truncation only bit payloads are reported decodable.

### Source excerpt

arXiv:2611.01162v1 Announce Type: cross Abstract: 4D Gaussian Splatting (4DGS) models are computationally expensive to train but distributed as easily copied parameter files. Existing watermarks protect these assets by fine-tuning the scene against a neural decoder to extract bit strings from rendered video, a heavy process vulnerable to the temporal dynamics of dynamic scenes. However, if the threat model targets the redistributed file itself, verification can be vastly simplified. Because the canonical Spherical-Harmonic (SH) coefficients of 4DGS are time- and view-invariant, parameter-space perturbations can be recovered via deterministic arithmetic. We propose **SHield**, the first non-blind, decoder-free watermarking approach that natively embeds full-resolution RGB images into 4DGS files. SHield tiles a zero-mean payload across the SH coefficients of a key-selected Gaussian subset, applying a brief anchored optimization to preserve visual fidelity. To verify ownership, it geometrically re-associates the key using canonical Gaussian centres to survive file tampering and recovers the payload in closed form. Across 30 scenes (D-NeRF, HyperNeRF, DyNeRF), SHield guarantees near-perfect payload recovery (Pearson $r \geq 0.991$) on all 150 tested models with a mean rendering penalty of $\leq 0.13$~dB. Held-out evaluation yields perfect detection on 400 true trials and zero false positives across $1{,}600$ wrong-subset null trials. We also strictly bound the method's robustness: SHield survives INT8 quantization and $30\%$ opacity pruning for the image payload, and on aggressive SH-degree-1 truncation bit payloads are still decodable.

## Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

DevFeed: [Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication](<https://devfeed.tech/articles/splaxel-efficient-distributed-training-of-3d-gaussian-splatting-for-large-scale-scene-reconstruction-via-pixel-level-communication-113761.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.18588>)

Author: Wenqi Jia, Zhewen Hu, Ying Huang, Jian Xu, Siyi Wu, Yangming Zhang, Yu Gong, Stavros Kalafatis, Yuke Wang, Wei Niu, Chengming Zhang, Ang Li, Sheng Di, Yuede Ji, Bo Fang, Miao Yin

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [distributed-training](<https://devfeed.tech/topics/distributed-training.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3dgs](<https://devfeed.tech/tags/3dgs.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [distributed-training](<https://devfeed.tech/tags/distributed-training.md>), [gaussian-splatting](<https://devfeed.tech/tags/gaussian-splatting.md>), [large](<https://devfeed.tech/tags/large.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [scale](<https://devfeed.tech/tags/scale.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Splaxel scales 3D Gaussian Splatting training by having each GPU render its local Gaussian subset and exchange partial pixel values for global composition, avoiding Gaussian-level synchronization. The abstract says this maintains mathematical consistency while keeping communication cost stable as scene size grows. Geometric and transmittance visibility prediction reduce redundant pixel communication, while conflict-free camera-view consolidation improves GPU utilization. On large-scale datasets with up to 120 million Gaussians, Splaxel reports up to 7.6x speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

### Source excerpt

arXiv:2606.18588v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

## VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

DevFeed: [VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph](<https://devfeed.tech/articles/vlsplat-vision-language-guided-object-centric-3d-gaussian-splatting-via-scene-graph-115239.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01939>)

Author: Yuntae Jeon, Younho Jeon, Sujin Jin, Sungho Jo, Seunghee Park

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3d-scene-understanding](<https://devfeed.tech/tags/3d-scene-understanding.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [graph](<https://devfeed.tech/tags/graph.md>), [vision-language-models](<https://devfeed.tech/tags/vision-language-models.md>)

### AI overview

VLSplat adds object-level semantic priors from vision-language models to mask-based semantic lifting for 3D Gaussian Splatting, then refines Gaussian representations using an object-group scene graph. Its intra-group module suppresses semantic noise within object groups; its inter-group module expands object support by adding structurally relevant candidates from neighboring groups. The abstract reports improved semantic consistency and structural completeness of object-level categories in indoor scene experiments. It does not provide quantitative results or further detail on the datasets or evaluation.

### Source excerpt

arXiv:2611.01939v1 Announce Type: cross Abstract: Learning semantic representations for 3D Gaussian Splatting has recently emerged as a promising direction for 3D scene understanding. However, existing 2D-to-3D semantic lifting approaches rely primarily on 2D segmentation supervision and lack object-level priors, causing the learned representation to be driven by local mask evidence rather than holistic object structure. In this paper, we present VLSplat, a vision-language guided approach for object-centric semantic lifting in 3D Gaussian Splatting. Our method augments mask-based lifting with object-level semantic priors derived from vision-language models and refines Gaussian representations using an object-group scene graph. The refinement is performed through two language-guided modules: intra-group refinement suppresses semantic noise within object groups, while inter-group acquisition expands object support regions by incorporating structurally relevant candidates from neighboring groups. Extensive experiments on indoor scene datasets demonstrate that VLSplat improves the semantic consistency and structural completeness of object-level categories. Our code and models are available at https://vlsplat.github.io/.

## NEW GUIDE: Computer Graphics Turbo Demos #CircuitPython #AdafruitLearningSystem @Adafruit

DevFeed: [NEW GUIDE: Computer Graphics Turbo Demos #CircuitPython #AdafruitLearningSystem @Adafruit](<https://devfeed.tech/articles/new-guide-computer-graphics-turbo-demos-circuitpython-adafruitlearningsystem-adafruit-112627.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/02/new-guide-computer-graphics-turbo-demos-circuitpython-adafruitlearningsystem-adafruit/>)

Author: Adafruit Learning System

Published: 2026-11-02T20:11:42Z

Content type: release

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Graphics](<https://devfeed.tech/topics/graphics.md>), [Content Creation / Rendering](<https://devfeed.tech/topics/content-creation-rendering.md>), [Ray Tracing / Path Tracing](<https://devfeed.tech/topics/ray-tracing-path-tracing.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [adafruit-learning-system](<https://devfeed.tech/tags/adafruit-learning-system.md>), [box](<https://devfeed.tech/tags/box.md>), [circuitpython](<https://devfeed.tech/tags/circuitpython.md>), [circuitpython-turbo](<https://devfeed.tech/tags/circuitpython-turbo.md>), [computer-graphics](<https://devfeed.tech/tags/computer-graphics.md>), [fruit-jam](<https://devfeed.tech/tags/fruit-jam.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [guide](<https://devfeed.tech/tags/guide.md>), [models](<https://devfeed.tech/tags/models.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [shaders](<https://devfeed.tech/tags/shaders.md>), [siggraph](<https://devfeed.tech/tags/siggraph.md>), [stanford](<https://devfeed.tech/tags/stanford.md>), [utah](<https://devfeed.tech/tags/utah.md>), [voxel](<https://devfeed.tech/tags/voxel.md>)

### AI overview

The guide runs classic computer graphics demos in CircuitPython on the Fruit Jam, using CircuitPython Turbo to pre-compile math-intensive code for speed. It features Voxel Space, Cornell Box path-trace rendering, metaballs, and shader-based 3D models of the Utah Teapot and Stanford bunny. The supplied text does not give setup instructions or performance measurements.

### Source excerpt

It's time to run some classic computer graphics demos in CircuitPython on the Fruit Jam. You'll feel like you're right back at SIGGRAPH in the golden olden days of CGI! By using CircuitPython Turbo you can pre-compile some intensely math-y bits of code for maximum speed. Check out these classic demos of Voxel Space, Cornell [...]

## Splatting the Gaussians into Blender

DevFeed: [Splatting the Gaussians into Blender](<https://devfeed.tech/articles/splatting-the-gaussians-into-blender-109136.md>)

Original publisher: [Read original article](<https://code.blender.org/2026/10/splatting-the-gaussians-into-blender/>)

Author: Anastasia Rudina

Published: 2026-10-30T13:18:52Z

Content type: article

Language: en

Sources: [Blender](<https://devfeed.tech/sources/blender.md>)

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [blender](<https://devfeed.tech/topics/blender.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [blender](<https://devfeed.tech/tags/blender.md>), [blender-5-3](<https://devfeed.tech/tags/blender-5-3.md>), [cycles](<https://devfeed.tech/tags/cycles.md>), [development](<https://devfeed.tech/tags/development.md>), [eevee](<https://devfeed.tech/tags/eevee.md>), [future](<https://devfeed.tech/tags/future.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [gaussian-splatting](<https://devfeed.tech/tags/gaussian-splatting.md>), [general-development](<https://devfeed.tech/tags/general-development.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [learn](<https://devfeed.tech/tags/learn.md>), [project](<https://devfeed.tech/tags/project.md>), [support](<https://devfeed.tech/tags/support.md>)

### AI overview

Blender 5.3 adds initial native support for importing, editing, and rendering 3D Gaussian splats from PLY and SPZ files or USDs. Blender represents splats as point clouds with position, 3D scale, quaternion rotation, and view-dependent radiance attributes. EEVEE and Workbench rasterize camera-facing billboards using dithered transparency; the stochastic approach can be noisy, so raising the sample count helps. Cycles instead intersects rays with splats using stochastic opacity, supporting reflections and indirect lighting but producing results that can differ from rasterized renderers, especially with data fitted for billboard rendering. Relighting is early-stage and estimates normals from each splat's smallest scale. The text identifies EEVEE overdraw, clunky point-cloud editing, and view-dependent radiance as areas needing improvement; future work may include GPU culling and albedo extraction.

### Source excerpt

Learn about the initial implementation of Gaussian splatting support in Blender and future development plans for this project.

## Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction

DevFeed: [Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction](<https://devfeed.tech/articles/honeycomb-surfels-compact-hexagonal-primitives-for-efficient-scene-rendering-and-reconstruction-103305.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37668>)

Author: Prakhar Kaushik, Soumava Paul, Alan Yuille

Published: 2026-10-28T04:00:00Z

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: [Computer Graphics & Visualization](<https://devfeed.tech/topics/computer-graphics-visualization.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-reconstruction](<https://devfeed.tech/tags/3d-reconstruction.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [also](<https://devfeed.tech/tags/also.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [area](<https://devfeed.tech/tags/area.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [color](<https://devfeed.tech/tags/color.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>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [domain](<https://devfeed.tech/tags/domain.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [elements](<https://devfeed.tech/tags/elements.md>), [error](<https://devfeed.tech/tags/error.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [field](<https://devfeed.tech/tags/field.md>), [fields](<https://devfeed.tech/tags/fields.md>), [rendering](<https://devfeed.tech/tags/rendering.md>)

### AI overview

Hexels represent scenes with planar hexagonal surface elements carrying a first-order spatial color field, using fewer, larger primitives to model locally planar regions with smoothly varying appearance. Across 34 scenes, they improve PSNR by 4.53-7.38 dB over memory-matched 2DGS while requiring less training VRAM; a per-primitive ablation reports up to 4.74 dB higher PSNR and 2.31x faster FPS. For surface reconstruction, Hexels reduce error by 28.9% on 15 DTU scans versus memory-matched 2DGS and achieve a higher mean F1 on six Tanks and Temples scenes (34.38% versus 31.72%). The abstract also reports improved 2D image representation over Image-GS, but gives no numerical comparison for that result.

### Source excerpt

arXiv:2610.37668v1 Announce Type: cross Abstract: Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for efficient 3D scene and 2D image representation. Hexels exploit locally planar regions with smoothly varying appearance using fewer, larger primitives. Their hexagonal support provides an area- and boundary-efficient domain, while the local color field captures appearance variation within each primitive. Across 34 scenes, Hexels improve PSNR over memory-matched 2DGS by 4.53-7.38 dB across datasets while requiring lower training VRAM. We further ablate Hexels by showing that per primitive, Hexels outperform 2DGS by upto 4.74 dB while using lower training VRAM and having 2.31 times faster FPS. Even in unconstrained settings, Hexels offers complementary quality-memory trade-offs. For efficient 3D surface reconstruction, Hexels reduce error by 28.9% compared with memory-matched 2DGS across 15 DTU scans. On 6 Tanks and Temples surface scenes, Hexels achieves the highest mean F1 among compared methods (34.38%, versus 31.72% for 2DGS). We further also show that Hexels, as a general primitive, improves 2D image representation over Image-GS. Hexels push the Pareto frontier on the quality-efficiency trade-off of surface-aligned primitives.

## Google introduces cutting-edge Genie 4 world model

DevFeed: [Google introduces cutting-edge Genie 4 world model](<https://devfeed.tech/articles/google-introduces-cutting-edge-genie-4-world-model-102794.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/27/google-introduces-cutting-edge-genie-4-world-model/>)

Author: Maria Deutscher

Published: 2026-10-28T01:10:58Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [World models](<https://devfeed.tech/topics/world-models.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [alphabet](<https://devfeed.tech/tags/alphabet.md>), [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audio](<https://devfeed.tech/tags/audio.md>), [car](<https://devfeed.tech/tags/car.md>), [deepmind](<https://devfeed.tech/tags/deepmind.md>), [developers](<https://devfeed.tech/tags/developers.md>), [gemini-4-argon](<https://devfeed.tech/tags/gemini-4-argon.md>), [gemini-omni](<https://devfeed.tech/tags/gemini-omni.md>), [genie-4](<https://devfeed.tech/tags/genie-4.md>), [google](<https://devfeed.tech/tags/google.md>), [llm](<https://devfeed.tech/tags/llm.md>), [nasdaq-goog](<https://devfeed.tech/tags/nasdaq-goog.md>), [news](<https://devfeed.tech/tags/news.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-3](<https://devfeed.tech/tags/top-story-3.md>), [top-story-4](<https://devfeed.tech/tags/top-story-4.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

Google previewed Genie 4, a world model that generates navigable 3D environments from natural-language prompts. Users can steer scenes with follow-up prompts or keyboard camera controls; the excerpt says edits such as changing weather or adding objects can preserve photorealism and consistency. Compared with its predecessor, Genie 4 reportedly handles fluid motion and complex details better, generates accompanying audio, and simulates people that respond to their surroundings. Google says Gemini Omni supplies realistic visual assets, while Gemini 3.8 Flash helps keep frames consistent by tracking goals and adapting plans as scenes change. DeepMind is exploring robotics simulations: Gemini 4 Argon can expand a high-level task into detailed prompts for workflow steps, with more precise prompts improving rendering and potential training usefulness. Genie 4 is being tested with limited early adopters; planned access includes Google AI Ultra, the Gemini API, and Google AI Studio.

### Source excerpt

Google LLC today previewed Genie 4, an artificial intelligence model that can generate realistic three-dimensional environments. The algorithm is the latest addition to a series of world models that the company launched in 2024. Compared with its predecessor, Genie 4 is better at rendering fluid movements and other complex details. Furthermore, it can generate accompanying [...] The post Google introduces cutting-edge Genie 4 world model appeared first on SiliconANGLE.

## Generate image 3D Modelling using Jetpack Compose WebGPU

DevFeed: [Generate image 3D Modelling using Jetpack Compose WebGPU](<https://devfeed.tech/articles/generate-image-3d-modelling-using-jetpack-compose-webgpu-100953.md>)

Original publisher: [Read original article](<https://proandroiddev.com/generate-image-3d-modelling-using-jetpack-compose-webgpu-a7fc2a01b3b1?source=rss----c72404660798---4>)

Author: Mikkel Septiano

Published: 2026-10-26T13:46:35Z

Content type: tutorial

Language: en

Sources: [ProAndroidDev](<https://devfeed.tech/sources/proandroiddev-medium.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D visualization](<https://devfeed.tech/topics/3d-visualization.md>), [Jetpack Compose](<https://devfeed.tech/topics/jetpack-compose.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-rendering](<https://devfeed.tech/tags/3d-rendering.md>), [android](<https://devfeed.tech/tags/android.md>), [android-app-development](<https://devfeed.tech/tags/android-app-development.md>), [image](<https://devfeed.tech/tags/image.md>), [jetpack-compose](<https://devfeed.tech/tags/jetpack-compose.md>), [mobile-apps](<https://devfeed.tech/tags/mobile-apps.md>), [opengl](<https://devfeed.tech/tags/opengl.md>), [webgpu](<https://devfeed.tech/tags/webgpu.md>)

### AI overview

The article introduces using WebGPU in Android with Jetpack Compose to turn a 2D image into a 3D visualization rendered on-device. It frames the project as a way to explore how graphics APIs, GPU processing, shaders, and rendering pipelines contribute to interactive results such as rotating objects. The supplied excerpt gives the motivation and broad aim but does not include implementation details.

### Source excerpt

Generate image 3D Modelling from 2D image using Jetpack Compose WebGPU Android Continue reading on ProAndroidDev "

## RADIANT: Object-Centric Feed-Forward Global Illumination

DevFeed: [RADIANT: Object-Centric Feed-Forward Global Illumination](<https://devfeed.tech/articles/radiant-object-centric-feed-forward-global-illumination-99555.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32075>)

Author: Sarah Zhang, Zhiyang Dou, Minghao Guo, Benjamin Tod Jones, Wojciech Matusik

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

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

Topics: [Ray Tracing / Path Tracing](<https://devfeed.tech/topics/ray-tracing-path-tracing.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [attention](<https://devfeed.tech/tags/attention.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [camera](<https://devfeed.tech/tags/camera.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [global](<https://devfeed.tech/tags/global.md>), [mesh](<https://devfeed.tech/tags/mesh.md>), [network](<https://devfeed.tech/tags/network.md>), [neural](<https://devfeed.tech/tags/neural.md>), [novel](<https://devfeed.tech/tags/novel.md>), [object](<https://devfeed.tech/tags/object.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [patch](<https://devfeed.tech/tags/patch.md>), [ray](<https://devfeed.tech/tags/ray.md>), [ray-tracing](<https://devfeed.tech/tags/ray-tracing.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

RADIANT reduces the effect of mesh resolution on feed-forward global illumination by representing each object with 32 surface-patch tokens, so attention length depends on object count rather than polygon count. Its scene transformer models radiative exchange between objects, while a view decoder renders target camera poses; invariant form-factor attention encodes geometry and learned area and material gains, and depth-tested point splats guide visibility without mesh connectivity. On a 1.03M-scene benchmark with matched model capacity, it reached 25 dB tone-mapped PSNR in one-fifth the training steps of RenderFormer and 32.2 dB at 600k steps--3.3 dB above RenderFormer and 7.6 dB above RenderFormer-V2. A 512x512 pass for a 500-object scene took 0.83 seconds; the abstract reports cost scaling with object count rather than polygon count.

### Source excerpt

arXiv:2610.32075v1 Announce Type: cross Abstract: Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing. Existing transformer-based renderers tokenize individual triangles, so self-attention scales quadratically with mesh resolution. Yet macroscopic radiative transport is governed by the underlying surface geometry and object arrangements rather than a particular mesh discretization; finer tessellation can thus inflate token counts without changing the underlying transport physics, motivating a discretization-agnostic and object-centric representation. We introduce RADIANT (RADiance-based Inter-Actor Neural Transformer), an object-centric architecture for feed-forward global illumination from point inputs. By representing each object with a compact budget of 32 surface-patch tokens, RADIANT decouples attention sequence length from polygon counts. In a single network, an inter-object scene transformer models 3D radiative exchange and a view decoder renders images at target camera poses. To capture light transport without materializing O(N^2) bias matrices, invariant form-factor attention embeds geometric distances and surface orientations directly into query-key dot products as SE(3)-invariant inner products weighted by learned area and material gains. For primary visibility without mesh connectivity, camera rays cross-attend scene tokens guided by depth-tested point splats in a shared spherical frame. Across a 1.03M-scene benchmark under matched model capacity, RADIANT reaches 25 dB tone-mapped PSNR in 5x fewer training steps than RenderFormer, and achieves 32.2 dB at 600k steps (+3.3 dB over RenderFormer and +7.6 dB over RenderFormer-V2). We further demonstrate the scalability of RADIANT, which completes a 512x512 forward pass of a 500-object scene in 0.83 s, with computational cost scaling with the number of objects rather than polygons.

## DLSS 5 Just Got a Lot Faster, but Is It Worth Using?

DevFeed: [DLSS 5 Just Got a Lot Faster, but Is It Worth Using?](<https://devfeed.tech/articles/dlss-5-just-got-a-lot-faster-but-is-it-worth-using-92560.md>)

Original publisher: [Read original article](<https://www.techspot.com/article/3190-dlss-5-performance-v2/>)

Author: Tim Schiesser

Published: 2026-10-21T10:08:00Z

Content type: comparison

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Graphics](<https://devfeed.tech/topics/graphics.md>), [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [1080p](<https://devfeed.tech/tags/1080p.md>), [2026](<https://devfeed.tech/tags/2026.md>), [4k](<https://devfeed.tech/tags/4k.md>), [5050](<https://devfeed.tech/tags/5050.md>), [article](<https://devfeed.tech/tags/article.md>), [but](<https://devfeed.tech/tags/but.md>), [dlss](<https://devfeed.tech/tags/dlss.md>), [dlss-5](<https://devfeed.tech/tags/dlss-5.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fps](<https://devfeed.tech/tags/fps.md>), [just](<https://devfeed.tech/tags/just.md>), [model](<https://devfeed.tech/tags/model.md>), [neural](<https://devfeed.tech/tags/neural.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [series](<https://devfeed.tech/tags/series.md>), [speed](<https://devfeed.tech/tags/speed.md>), [test](<https://devfeed.tech/tags/test.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

In NBA 2K27, Nvidia's October DLSS 5 model substantially reduces neural-rendering time across tested RTX 50 GPUs, making the feature more usable while still imposing a large frame-rate cost. The article measures average speedups of 83% at 4K and 94% at 1440p versus the prior model; for example, an RTX 5080 rises from 53 to 78 FPS at 4K, but remains 58% below performance with DLSS 5 off. The updated model delivers broadly similar image quality, yet the tested game still shows lighting flicker, inconsistent skin appearance at distance, and halo artifacts around characters; the authors say the halo may be more noticeable. Their judgment is that this is a meaningful performance optimization, not a complete fix: visual issues remain and the feature can still cost substantial FPS. Results are from one game and the tested RTX 50 series, so they do not establish behavior across other titles or GPU generations.

### Source excerpt

Nvidia's new DLSS 5 model nearly doubles neural rendering speed across the RTX 50 series. We put it to the test to see if the performance gains outweigh the heavy FPS penalty and lingering visual issues. Read Entire Article

## Exploring WebGPU on Android: Turning a 2D Image into a 3D Relief with Jetpack Compose

DevFeed: [Exploring WebGPU on Android: Turning a 2D Image into a 3D Relief with Jetpack Compose](<https://devfeed.tech/articles/exploring-webgpu-on-android-turning-a-2d-image-into-a-3d-relief-with-jetpack-compose-91131.md>)

Original publisher: [Read original article](<https://proandroiddev.com/exploring-webgpu-on-android-turning-a-2d-image-into-a-3d-relief-with-jetpack-compose-8cd60b655860?source=rss----c72404660798---4>)

Author: Samuel

Published: 2026-10-20T16:26:21Z

Content type: tutorial

Language: en

Sources: [ProAndroidDev](<https://devfeed.tech/sources/proandroiddev-medium.md>)

Topics: [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [Jetpack Compose](<https://devfeed.tech/topics/jetpack-compose.md>), [shaders](<https://devfeed.tech/topics/shaders.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Android](<https://devfeed.tech/topics/android.md>), [Image](<https://devfeed.tech/topics/image.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-image-rendering](<https://devfeed.tech/tags/3d-image-rendering.md>), [android](<https://devfeed.tech/tags/android.md>), [android-app-development](<https://devfeed.tech/tags/android-app-development.md>), [compose](<https://devfeed.tech/tags/compose.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [image](<https://devfeed.tech/tags/image.md>), [jetpack](<https://devfeed.tech/tags/jetpack.md>), [jetpack-compose](<https://devfeed.tech/tags/jetpack-compose.md>), [shaders](<https://devfeed.tech/tags/shaders.md>), [webgpu](<https://devfeed.tech/tags/webgpu.md>)

### AI overview

The tutorial describes an Android app that renders a photo as a GPU-drawn 3D relief: brighter pixels become higher terrain and darker pixels lower terrain. Kotlin scales the image to a 64 x 64 grid, converts pixels to normalized BT.601 luminance values, and embeds those heights in WGSL shader code. The vertex shader derives a triangle mesh from vertex indices and applies an isometric projection; the fragment shader colors low, middle, and high areas navy, teal, and near-white. Jetpack Compose hosts the WebGPU surface and UI, while coroutine cancellation triggers GPU cleanup. The example uses AndroidX WebGPU 1.0.0-alpha06 and Coil, requires a physical Android device with API 26 or higher and a modern GPU, and cautions that the WebGPU library is still in alpha, so its current version should be checked.

### Source excerpt

This image is AI generatedOverview In this tutorial, you will build an Android app that turns an ordinary photo into a 3D landscape. Bright areas of the image rise into hills, dark areas sink into valleys, and the result is drawn directly on the GPU using the AndroidX WebGPU library and Jetpack Compose. How it works The whole technique rests on one rule: the brighter a pixel is, the higher it sits. The app processes an image in five stages: The user picks an image from the device. The image is resized to a 64 x 64 grid. The brightness of each pixel is calculated. Those values are stored in a height map. A shader reads the height map and draws a 3D-looking surface. Two small GPU programs, called shaders and written in WGSL (WebGPU Shading Language), do the drawing: The vertex shader decides where each point of the surface appears on screen. The fragment shader decides what color each pixel should be. Project files The app is split into three files, each with a single responsibility: WebGpuRenderer.ktImage processing, shaders, and GPU drawingWebGpuSurface.ktConnects Compose to the renderer and manages the drawing surfaceMainActivity.ktThe UI: pick an image, preview it, and tap Generate 3DPrerequisites Android Studio with Jetpack Compose support Basic knowledge of Kotlin and Compose A physical Android device (API 26 or higher) with a modern GPU No previous graphics programming experience is required. Step 1: Create the Project and Add Dependencies In Android Studio, select File -> New -> New Project and choose the Empty Activity template. Set the Minimum SDK to API 26. Open your module's build.gradle.kts and add the WebGPU library and Coil (used for the image preview): dependencies { implementation("androidx.webgpu:webgpu:1.0.0-alpha06") implementation("io.coil-kt:coil-compose:<latest-version>") } Sync the project. Create two new Kotlin files next to MainActivity.kt: WebGpuRenderer.kt and WebGpuSurface.kt. Tip: the WebGPU library is still in alpha. Check the AndroidX Web

[Next page](<https://devfeed.tech/topics/3d-rendering.md?cursor=WyIyMDI2LTEwLTIwVDE2OjI2OjIxKzAwOjAwIiwgImQzMGY4ZmVkLTNhMzItNDFkMi1hYzhhLTZiNWUyOWUyMDdhYiJd>)