Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917259777146880 |
|---|---|
| author | Zhang, Shuo Wu, Wenzhuo Zhang, Huayu Cheng, Jiarong Zang, Xianghao Ban, Chao Sun, Hao He, Zhongjiang Cao, Tianwei Liang, Kongming Ma, Zhanyu |
| author_facet | Zhang, Shuo Wu, Wenzhuo Zhang, Huayu Cheng, Jiarong Zang, Xianghao Ban, Chao Sun, Hao He, Zhongjiang Cao, Tianwei Liang, Kongming Ma, Zhanyu |
| contents | Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particularly in complex scenes. Existing approaches suffer from two main limitations: (1) difficulty in achieving accurate geometric editing of object translation, rotation, and scaling; (2) inadequate modeling of intricate lighting and shadow effects, leading to unrealistic results. To address these issues, we propose GeoEdit, a framework that leverages in-context generation through a diffusion transformer module, which integrates geometric transformations for precise object edits. Moreover, we introduce Effects-Sensitive Attention, which enhances the modeling of intricate lighting and shadow effects for improved realism. To further support training, we construct RS-Objects, a large-scale geometric editing dataset containing over 120,000 high-quality image pairs, enabling the model to learn precise geometric editing while generating realistic lighting and shadows. Extensive experiments on public benchmarks demonstrate that GeoEdit consistently outperforms state-of-the-art methods in terms of visual quality, geometric accuracy, and realism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08388 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers Zhang, Shuo Wu, Wenzhuo Zhang, Huayu Cheng, Jiarong Zang, Xianghao Ban, Chao Sun, Hao He, Zhongjiang Cao, Tianwei Liang, Kongming Ma, Zhanyu Computer Vision and Pattern Recognition Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particularly in complex scenes. Existing approaches suffer from two main limitations: (1) difficulty in achieving accurate geometric editing of object translation, rotation, and scaling; (2) inadequate modeling of intricate lighting and shadow effects, leading to unrealistic results. To address these issues, we propose GeoEdit, a framework that leverages in-context generation through a diffusion transformer module, which integrates geometric transformations for precise object edits. Moreover, we introduce Effects-Sensitive Attention, which enhances the modeling of intricate lighting and shadow effects for improved realism. To further support training, we construct RS-Objects, a large-scale geometric editing dataset containing over 120,000 high-quality image pairs, enabling the model to learn precise geometric editing while generating realistic lighting and shadows. Extensive experiments on public benchmarks demonstrate that GeoEdit consistently outperforms state-of-the-art methods in terms of visual quality, geometric accuracy, and realism. |
| title | Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.08388 |