AI Paper Atlas

Research map / Image generation / Editing and style transfer

Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models

Yujia Yang, Yuanxiang Wang, Zhenyu Guan, Tiankun Yang, Chenxi Bao, Haopeng Jin, Jinwen Luo, Xinyu Zuo, Lisheng Duan, Haijin Liang, Jin Ma, Xinming Wang and 2 more

CVPR 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 2 citations (OpenAlex)

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
move from single-turn to multi-turn editingQwen-image-edit · Omni IIE BenchSSIM: 0.455 -> 0.391Hurt
move from single-turn to multi-turn editingQwen-image-edit · Omni IIE BenchOverall: 0.687 -> 0.676Hurt
move from single-turn to multi-turn editingMGIE · Omni IIE BenchOverall: 0.520 -> 0.404Hurt
move from single-turn to multi-turn editingInstructPix2Pix · Omni IIE BenchOverall: 0.530 -> 0.549Mixed
move from single-turn to multi-turn editingQwen-image-edit · Omni IIE BenchQA instruction compliance: 0.744 -> 0.818Improved
evaluate instruction compliance with QA in addition to image-similarity metricsMGIE · Omni IIE Bench single-turnQA instruction compliance: 0.070Hurt

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