Research map / Image generation / Editing and style transfer
WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
Kaihang Pan, Weile Chen, Haiyi Qiu, Qifan Yu, Wendong Bu, Zehan Wang, Yun Zhu, Juncheng Li, Siliang Tang
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 |
|---|---|---|---|
| rewrite instruction with knowledge hint (ablation) | Bagel · WiseEdit subset (75 cases) | Knowledge Fidelity: 50.2 -> 78.4 | Improved |
| rewrite instruction with knowledge hint (ablation) | Qwen-Image-Edit · WiseEdit subset (75 cases) | Overall AVG: 52.1 -> 66.2 | Improved |
| rewrite instruction with knowledge hint (ablation) | Nano Banana · WiseEdit subset (75 cases) | Overall AVG: 70.4 -> 75.0 | Improved |
| rewrite instruction with knowledge hint (ablation) | GPT-image-1 · WiseEdit subset (75 cases) | Overall AVG: 68.2 -> 74.2 | Improved |
| use unified comprehension-generation architecture instead of pure diffusion | image editing models · WiseEdit | AVG score | Improved |
| disable built-in thinking process (ablation) | Bagel and DreamOmni2 · WiseEdit and WiseEdit-Complex | AVG score | Hurt |
| multi-image inputs instead of single-image | image editing models · WiseEdit | AVG score | Hurt |
| complex task (all three steps hard) vs the three single-step tasks | closed-source models · WiseEdit-Complex | IF | Hurt |
| closed-source vs open-source models | Nano Banana Pro vs FLUX.2 Dev · WiseEdit overall (English) | AVG score: 61.8 -> 82.4 | Improved |
Closest papers by meaning
- KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models (NeurIPS 2025 · similarity 0.91)
- ReasonEdit: Towards Reasoning-Enhanced Image Editing Models (CVPR 2026 · similarity 0.88)
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025 · similarity 0.87)
- IDEA-Bench: How Far are Generative Models from Professional Designing? (CVPR 2025 · similarity 0.87)
- Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing (NeurIPS 2025 · similarity 0.87)
- Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning (ICML 2026 · similarity 0.86)
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.
