# One Evaluation Is Enough: Inversion-Free Image Editing with Trajectory Correction

DevFeed: [One Evaluation Is Enough: Inversion-Free Image Editing with Trajectory Correction](<https://devfeed.tech/articles/one-evaluation-is-enough-inversion-free-image-editing-with-trajectory-correction-98121.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30827>)

Author: Lifan Jiang, Taiyang Chen, Senlin cheng, Bolei Xu, Xiaobo Li, Can Ye, Dehai Zhao, Deng Cai, Boxi Wu

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

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

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

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [angular](<https://devfeed.tech/tags/angular.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [batch](<https://devfeed.tech/tags/batch.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [can](<https://devfeed.tech/tags/can.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [duality](<https://devfeed.tech/tags/duality.md>), [editor](<https://devfeed.tech/tags/editor.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [field](<https://devfeed.tech/tags/field.md>), [fields](<https://devfeed.tech/tags/fields.md>), [first](<https://devfeed.tech/tags/first.md>), [form](<https://devfeed.tech/tags/form.md>), [free](<https://devfeed.tech/tags/free.md>), [generators](<https://devfeed.tech/tags/generators.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [image](<https://devfeed.tech/tags/image.md>), [image-editing](<https://devfeed.tech/tags/image-editing.md>), [integrate](<https://devfeed.tech/tags/integrate.md>), [with](<https://devfeed.tech/tags/with.md>)

## AI overview

Endpoint-Calibrated Transport (ECT) edits real images in one latent update without inversion or iterative optimization. In a variance-preserving one-step model, a single source-target query at a shared noisy state provides both a local semantic tangent and a clean endpoint displacement. ECT integrates the tangent over the remaining VP angle, then uses a constrained projection based on the endpoint displacement to correct the long-range transport. It is training-free and uses one noise level, two text conditions in one denoiser batch, and pretrained epsilon-prediction VP generators. The abstract reports stable editing-quality gains across its benchmark settings and very short editing time; it does not provide benchmark details or quantify those gains.

## Source excerpt

arXiv:2610.30827v1 Announce Type: cross Abstract: Real-image editing commonly relies on inversion and iterative sampling, while efficient one-step editors often stabilize a large update by estimating and averaging editing fields at multiple noise levels. We ask a stricter question: is a single temporal field evaluation sufficient for reliable inversion-free editing? Our answer rests on a previously underused duality in a variance-preserving (VP) one-step model: one source-target query at a shared noisy state simultaneously determines a local angular semantic tangent and a clean endpoint displacement. We integrate the tangent over the analytically known remaining VP angle to obtain a nominal one-step transport, and use the endpoint displacement to correct its long-horizon extrapolation through a constrained projection. This transport-first, correction-second construction yields Endpoint-Calibrated Transport (ECT), a closed-form, training-free editor requiring only one noise level, two text conditions packed into one denoiser batch, and one latent update. ECT requires no image inversion, trajectory integration, second temporal observation, or iterative optimization, and can be directly applied to pretrained epsilon-prediction VP one-step generators. Across the reported benchmark settings, ECT delivers stable gains in editing quality within an extremely short editing time.