Training-free Geometric Image Editing on Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911086509293568 |
|---|---|
| author | Zhu, Hanshen Zhu, Zhen Zhang, Kaile Gong, Yiming Liu, Yuliang Bai, Xiang |
| author_facet | Zhu, Hanshen Zhu, Zhen Zhang, Kaile Gong, Yiming Liu, Yuliang Bai, Xiang |
| contents | We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant subtasks in a single step, proving difficult when transformations become large or structurally complex. We address this by proposing a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement. Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine. In experiments on our new GeoBench benchmark, which contains both 2D and 3D editing scenarios, FreeFine outperforms state-of-the-art alternatives in image fidelity, and edit precision, especially under demanding transformations. Code and benchmark are available at: https://github.com/CIawevy/FreeFine |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23300 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training-free Geometric Image Editing on Diffusion Models Zhu, Hanshen Zhu, Zhen Zhang, Kaile Gong, Yiming Liu, Yuliang Bai, Xiang Computer Vision and Pattern Recognition We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant subtasks in a single step, proving difficult when transformations become large or structurally complex. We address this by proposing a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement. Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine. In experiments on our new GeoBench benchmark, which contains both 2D and 3D editing scenarios, FreeFine outperforms state-of-the-art alternatives in image fidelity, and edit precision, especially under demanding transformations. Code and benchmark are available at: https://github.com/CIawevy/FreeFine |
| title | Training-free Geometric Image Editing on Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.23300 |