Research map / Image generation / Editing and style transfer
EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
Wei Chow, Linfeng Li, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan and 4 more
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 |
|---|---|---|---|
| use EditMGT instead of FluxKontext.dev on style tasks | EditMGT · GEdit-EN-full | Style score: 5.55 -> 6.53 | Improved |
| use EditMGT instead of VAREdit-8B | EditMGT · GEdit-EN-full | Overall score: 5.73 -> 5.87 | Improved |
| use EditMGT instead of FluxKontext.dev overall | EditMGT · GEdit-EN-full | Overall score: 6.26 -> 5.87 | Hurt |
| use EditMGT instead of FluxKontext.dev on text editing | EditMGT · GEdit-EN-full | Text score: 6.10 -> 4.53 | Hurt |
| use EditMGT instead of VAREdit-8B on MagicBrush DINO | EditMGT · MagicBrush test | DINO: 0.844 -> 0.881 | Improved |
| use EditMGT instead of AnyEdit on L1 | EditMGT · Emu Edit test | L1: 0.070 -> 0.093 | Hurt |
| raise region-hold threshold lambda (ablation) | EditMGT · EditMGT | GEdit-Bench | Mixed |
| use Gemma2-IT-2B as text encoder (ablation) | EditMGT · EditMGT | GEdit-Bench Overall | Improved |
| scale training steps / data (ablation) | EditMGT · EditMGT | GEdit-Bench Overall | Improved |
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 5 of 8 shared results
- 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
- Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks (AAAI 2024 · similarity 0.90)
- Click2Mask: Local Editing with Dynamic Mask Generation (AAAI 2025 · similarity 0.90)
- Stable Flow: Vital Layers for Training-Free Image Editing (CVPR 2025 · similarity 0.89)
- Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing (CVPR 2024 · similarity 0.89)
- Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (NeurIPS 2025 · similarity 0.88)
- FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model (CVPR 2025 · similarity 0.88)
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.
