Research map / Image generation / Editing and style transfer
WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
Wang Lin, Feng Wang, Majun Zhang, Wentao Hu, Tao Jin, Zhou Zhao, Fei Wu, Jingyuan Chen, Sucheng Ren, Alan Yuille
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add image quality reward to RL (ablation) | Ours (Flow-GRPO on Bagel) · WorldEdit-Test | overall score: 3.85 -> 4.07 | Improved |
| add CoT reasoning reward to RL (ablation) | Ours (Flow-GRPO on Bagel) · WorldEdit-Test | overall score: 3.94 -> 4.07 | Improved |
| add causal verification reward to RL (ablation) | Ours (Flow-GRPO on Bagel) · WorldEdit-Test | overall score: 3.91 -> 4.07 | Improved |
| fine-tune Bagel on WorldEdit data with two-stage training and rewards | Bagel · WorldEdit-Test | overall score: 2.76 -> 4.07 | Improved |
| rewrite instructions into paraphrased explicit instructions | Bagel · WorldEdit-Test | overall score: 2.76 -> 3.01 | Improved |
| fine-tune on WorldEdit instead of only paraphrasing instructions | Bagel · WorldEdit-Test | overall score: 3.01 -> 4.07 | Improved |
| paraphrase instructions for Omnigen2 | Omnigen2 · WorldEdit-Test | overall score: 2.51 -> 2.62 | Improved |
| paraphrase instructions for GPT-4o | GPT-4o · WorldEdit-Test | overall score: 4.36 -> 4.38 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Anyedit — AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025) · better on 1 of 1 shared result
- Omnigen — OmniGen: Unified Image Generation (CVPR 2025) · better on 1 of 1 shared result
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
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025 · similarity 0.89)
- UltraEdit: Instruction-based Fine-Grained Image Editing at Scale (NeurIPS 2024 · similarity 0.89)
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.89)
- InsightEdit: Towards Better Instruction Following for Image Editing (CVPR 2025 · similarity 0.89)
- Learning Action and Reasoning-Centric Image Editing from Videos and Simulation (NeurIPS 2024 · similarity 0.89)
- FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model (CVPR 2025 · similarity 0.89)
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.
