Research map / Vision-language and multimodal / Human and embodied modeling
Responsible Visual Editing
Minheng Ni, Yeli Shen, Lei Zhang, Wangmeng Zuo
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 perceptual cognitive process (locate the region to edit with LMM and numbered masks) (ablation) | CoEditor · AltBear | success rate: 43.98% -> 65.43% | Improved |
| add behavioral cognitive process (LMM plans modification target prompt) (ablation) | CoEditor · AltBear | success rate: 26.00% -> 65.43% | Improved |
| add behavioral cognitive process (ablation) | CoEditor · AltBear | modified pixel ratio: 59.2% -> 58.6% | Improved |
| use LMM-guided CoEditor instead of InstructDiffusion | responsible visual editing · AltBear (machine eval, overall) | success rate: 43.31% -> 65.43% | Improved |
| evaluate on real images instead of AltBear teddy-bear images | CoEditor · machine eval, overall | success rate: 65.43% -> 60.00% | No clear effect |
| use larger Semantic-SAM granularity (ablation) | CoEditor · qualitative examples | edit extent | Mixed |
| use LMM-based pipeline instead of end-to-end editor | CoEditor · inference time | time per image: 12.43s -> 14.10s | Mixed |
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.
- InstructDiffusion — InstructDiffusion: A Generalist Modeling Interface for Vision Tasks (CVPR 2024) · better on 10 of 10 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
- ORES: Open-Vocabulary Responsible Visual Synthesis (AAAI 2024 · similarity 0.85)
- Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing (NeurIPS 2024 · similarity 0.85)
- Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually (AAAI 2024 · similarity 0.83)
- Learning Action and Reasoning-Centric Image Editing from Videos and Simulation (NeurIPS 2024 · similarity 0.83)
- VicEdit: Learning to Edit Videos from Visual In-Context Examples (NeurIPS 2026 · similarity 0.83)
- HIVE: Harnessing Human Feedback for Instructional Visual Editing (CVPR 2024 · similarity 0.83)
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.
