Research map / Image generation / Editing and style transfer
Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
Shuo Zhang, Wenzhuo Wu, Huayu Zhang, Jiarong Cheng, Xianghao Zang, Chao Ban, Hao Sun, Zhongjiang He, Tianwei Cao, Kongming Liang, Zhanyu Ma
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 |
|---|---|---|---|
| replace standard attention with Effects-Sensitive Attention (ablation) | GeoEdit · GeoBench 2D-edits | FID: 29.11 -> 25.28 | Improved |
| replace standard attention with Effects-Sensitive Attention (ablation) | GeoEdit · GeoBench 3D-edits | FID: 68.02 -> 64.30 | Improved |
| use soft ESA instead of Hard Modulation (ablation) | GeoEdit · GeoBench 2D-edits | FID: 27.09 -> 25.28 | Improved |
| use soft ESA instead of Hard Modulation (ablation) | GeoEdit · GeoBench 3D-edits | Warp error: 0.061 -> 0.051 | Improved |
| add Hard Modulation over standard attention (ablation) | GeoEdit · GeoBench 2D-edits | Background consistency: 0.969 -> 0.964 | Hurt |
| add AIGC data to rendered data (ablation) | GeoEdit · GeoBench 2D-edits | FID: 26.14 -> 25.28 | Improved |
| add rendered data to AIGC data (ablation) | GeoEdit · GeoBench 3D-edits | DINOv2 distance: 364.59 -> 350.69 | Improved |
| use alpha1=0.1, alpha2=1 instead of alpha1=1.0, alpha2=0.1 (ablation) | ESA · GeoBench 2D-edits | FID: 27.09 -> 25.28 | Improved |
| use alpha2=1 instead of 0.1 with alpha1=0.1 (ablation) | ESA · GeoBench 2D-edits | FID: 26.07 -> 25.28 | 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.
- DesignEdit — DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework (AAAI 2025) · better on 3 of 3 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
- GeoRemover: Removing Objects and Their Causal Visual Artifacts (NeurIPS 2025 · similarity 0.87)
- DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework (AAAI 2025 · similarity 0.86)
- PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement (NeurIPS 2025 · similarity 0.86)
- ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing (NeurIPS 2024 · similarity 0.86)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · similarity 0.86)
- Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D (CVPR 2024 · similarity 0.85)
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.
