EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912449928626176 |
|---|---|
| author | Bar-On, Roi Cohen-Bar, Dana Cohen-Or, Daniel |
| author_facet | Bar-On, Roi Cohen-Bar, Dana Cohen-Or, Daniel |
| contents | We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks, EditP23 enables intuitive edits by conditioning on a pair of images: an original view and its user-edited counterpart. These image prompts are used to guide an edit-aware flow in the latent space of a pre-trained multi-view diffusion model, allowing the edit to be coherently propagated across views. Our method operates in a feed-forward manner, without optimization, and preserves the identity of the original object, in both structure and appearance. We demonstrate its effectiveness across a range of object categories and editing scenarios, achieving high fidelity to the source while requiring no manual masks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EditP23: 3D Editing via Propagation of Image Prompts to Multi-View Bar-On, Roi Cohen-Bar, Dana Cohen-Or, Daniel Graphics Computer Vision and Pattern Recognition 68U05 (Primary), 68T45 (Secondary) I.3.7; I.3.8; I.4.9 We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks, EditP23 enables intuitive edits by conditioning on a pair of images: an original view and its user-edited counterpart. These image prompts are used to guide an edit-aware flow in the latent space of a pre-trained multi-view diffusion model, allowing the edit to be coherently propagated across views. Our method operates in a feed-forward manner, without optimization, and preserves the identity of the original object, in both structure and appearance. We demonstrate its effectiveness across a range of object categories and editing scenarios, achieving high fidelity to the source while requiring no manual masks. |
| title | EditP23: 3D Editing via Propagation of Image Prompts to Multi-View |
| topic | Graphics Computer Vision and Pattern Recognition 68U05 (Primary), 68T45 (Secondary) I.3.7; I.3.8; I.4.9 |
| url | https://arxiv.org/abs/2506.20652 |