Research map / Image generation / Editing and style transfer
Group Editing: Edit Multiple Images in One Go
Yue Ma, Xinyu Wang, Qianli Ma, Qinghe Wang, Mingzhe Zheng, Xiangpeng Yang, Hao Li, Chongbo Zhao, Jixuan Ying, Harry Yang, Hongyu Liu, Qifeng Chen
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 VGGT explicit correspondence features (ablation) | GroupEditing · GroupEditBench | Editing Consis.: 0.8616 -> 0.9239 | Improved |
| add geometry-enhanced RoPE (Ge-RoPE) (ablation) | GroupEditing · GroupEditBench | Editing Consis.: 0.8697 -> 0.9239 | Improved |
| add Identity-RoPE (ablation) | GroupEditing · GroupEditBench | Editing Consis.: 0.9108 -> 0.9239 | Improved |
| add VGGT explicit correspondence features (ablation) | GroupEditing · GroupEditBench | Aesthetic-Score: 4.72 -> 5.39 | Improved |
| add Identity-RoPE (ablation) | GroupEditing · GroupEditBench | Aesthetic-Score: 4.89 -> 5.39 | Improved |
| treat image group as pseudo-video on a video diffusion backbone (GroupEditing vs Edicho) for local editing | GroupEditing · GroupEditBench (local) | Editing Consis.: 0.8988 -> 0.9239 | Improved |
| GroupEditing vs best baseline on global editing | GroupEditing · GroupEditBench (global) | DINO-Score: 0.8714 -> 0.9287 | Improved |
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.
- OminiControl — OminiControl: Minimal and Universal Control for Diffusion Transformer (ICCV 2025) · better on 5 of 5 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
- GroupDiff: Diffusion-based Group Portrait Editing (ECCV 2024 · similarity 0.87)
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · similarity 0.86)
- MotionEditGS: Editing Motion and Appearance of 4D Scenes from Monocular Video via Semantically Anchored Gaussians (ECCV 2026 · similarity 0.86)
- Learning Action and Reasoning-Centric Image Editing from Videos and Simulation (NeurIPS 2024 · similarity 0.84)
- Pathways on the Image Manifold: Image Editing via Video Generation (CVPR 2025 · similarity 0.84)
- Text-Vision Co-Instructed Image Editing (NeurIPS 2026 · similarity 0.84)
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.
