AI Paper Atlas

Research map / Image generation / Editing and style transfer

A²-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks

华渝 郑, Guangzhao Li, Baixuan Zhao, Siqi Luo, Hantao Jiang, Guangtao Zhai, Xiaohong Liu

ECCV 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific 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 Mixture of Transformers (routing over attention and FFN) instead of FFN-only MoE (ablation)A2-Edit · UniEdit test (rough mask)DINO-I: 56.11 -> 62.28Improved
add the full A2-Edit framework instead of baseline (ablation)FLUX.1 Fill · UniEdit test (fine mask)VLM score: 64.3 -> 82.3Improved
add FFN-only MoE over baseline (ablation)FLUX.1 Fill · UniEdit test (fine mask)VLM score: 64.3 -> 70.3Improved
add UniEdit-500K training data (ablation)A2-Edit · UniEdit test (rough mask)FID: 72.84 -> 54.62Improved
add UniEdit-500K training data (ablation)A2-Edit · UniEdit test (fine mask)DINO-I: 58.64 -> 61.71Improved
add augmented rough mask training after fine mask training (ablation)A2-Edit (MATS) · UniEdit test (rough mask)DINO-I: 55.65 -> 59.70Improved
add augmented rough mask training after fine mask training (ablation)A2-Edit (MATS) · UniEdit test (rough mask)FID: 74.77 -> 60.33Improved
add bounding box training stage (ablation)A2-Edit (MATS) · UniEdit test (rough mask)DINO-I: 59.70 -> 62.28Improved
add bounding box training stage (ablation)A2-Edit (MATS) · UniEdit test (rough mask)VLM score: 73.0 -> 79.3Improved
train with fine masks only (ablation)A2-Edit · UniEdit test (rough mask)DINO-I: 56.27 -> 55.65Hurt
train LiDiff-style baseline Insert Anything vs A2-Edit on rough maskA2-Edit · VITON-HD (rough mask)DINO-I: 60.87 -> 63.79Improved
use A2-Edit on UniEdit test (rough mask) vs ACE++A2-Edit · UniEdit test (rough mask)FID: 63.19 -> 54.62Improved

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