AI Paper Atlas

Research map / Image generation / Editing and style transfer

EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

Zexuan Yan, Yue Ma, Chang Zou, Wenteng Chen, Qifeng Chen, Linfeng Zhang

ICCV 2025 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial locality caching with inversion step skipping and TIPFLUX RF-inversion editing · Cache comparisonlatency speedup: 2.46x latency, 3.53x FLOPsImproved
add token index preprocessing (TIP) to SLoC (ablation)SLoC · Prompt editinginference time: 5.96 -> 5.14Improved
add inversion step skipping (ISS) to SLoC (ablation)SLoC · Prompt editinginference time: 5.96 -> 5.06Improved
add TIP and ISS together to SLoC (ablation)SLoC · Prompt editinginference time: 5.96 -> 4.60Improved
add TIP and ISS to SLoC (ablation)SLoC · Dragginginference time: 7.12 -> 5.66Improved
add TIP and ISS to SLoC (ablation)SLoC · Compositioninference time: 7.25 -> 5.66Improved
add TIP and ISS to SLoC (ablation)SLoC · DraggingFG fidelity FID: 20.61 -> 22.07Hurt
add TIP and ISS to SLoC (ablation)SLoC · Prompt editingFG fidelity FID: 39.50 -> 39.21Improved
skip inversion steps (2-step skip) instead of full inversion (ablation)SLoC · Prompt editinginference time: 13.27 -> 10.16Improved
increase inversion skip interval to 4 (ablation)SLoC · Prompt editinginference time: 13.27 -> 8.76Improved
skip denoising steps instead of inversion steps (ablation)SLoC · Prompt editingFG fidelity FID: 3.23 -> 64.10Hurt
use SLoC token scoring instead of ToCa/DuCa cachingFLUX editing · Cache comparisonFG FID: 84.77 -> 39.50Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy