V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909538318286848 |
|---|---|
| author | Zhang, Yanming Chen, Jun-Kun Lyu, Jipeng Wang, Yu-Xiong |
| author_facet | Zhang, Yanming Chen, Jun-Kun Lyu, Jipeng Wang, Yu-Xiong |
| contents | This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach employs a progressive strategy that decomposes complex editing tasks into a sequence of simpler subtasks. Each subtask is controlled through three key synergistic mechanisms: the initial noise, noise added at each denoising step, and cross-attention maps between text prompts and video content. This ensures robust preservation of original video elements while effectively applying the desired edits. Beyond its native video editing capability, we extend V$^2$Edit to 3D scene editing via a "render-edit-reconstruct" process, enabling high-quality, 3D-consistent edits even for tasks involving substantial geometric changes such as object insertion. Extensive experiments demonstrate that our V$^2$Edit achieves high-quality and successful edits across various challenging video editing tasks and complex 3D scene editing tasks, thereby establishing state-of-the-art performance in both domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10634 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes Zhang, Yanming Chen, Jun-Kun Lyu, Jipeng Wang, Yu-Xiong Computer Vision and Pattern Recognition This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach employs a progressive strategy that decomposes complex editing tasks into a sequence of simpler subtasks. Each subtask is controlled through three key synergistic mechanisms: the initial noise, noise added at each denoising step, and cross-attention maps between text prompts and video content. This ensures robust preservation of original video elements while effectively applying the desired edits. Beyond its native video editing capability, we extend V$^2$Edit to 3D scene editing via a "render-edit-reconstruct" process, enabling high-quality, 3D-consistent edits even for tasks involving substantial geometric changes such as object insertion. Extensive experiments demonstrate that our V$^2$Edit achieves high-quality and successful edits across various challenging video editing tasks and complex 3D scene editing tasks, thereby establishing state-of-the-art performance in both domains. |
| title | V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.10634 |