O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
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_ | 1866914017006583808 |
|---|---|
| author | Chen, Yuqing Wang, Junjie Liu, Lin Chu, Ruihang Zhang, Xiaopeng Tian, Qi Yang, Yujiu |
| author_facet | Chen, Yuqing Wang, Junjie Liu, Lin Chu, Ruihang Zhang, Xiaopeng Tian, Qi Yang, Yujiu |
| contents | Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current methods require different control signal for diverse editing tasks, which complicates model design and demands significant training resources. To address this, we propose O-DisCo-Edit, a unified framework that incorporates a novel object distortion control (O-DisCo). This signal, based on random and adaptive noise, flexibly encapsulates a wide range of editing cues within a single representation. Paired with a "copy-form" preservation module for preserving non-edited regions, O-DisCo-Edit enables efficient, high-fidelity editing through an effective training paradigm. Extensive experiments and comprehensive human evaluations consistently demonstrate that O-DisCo-Edit surpasses both specialized and multitask state-of-the-art methods across various video editing tasks. https://cyqii.github.io/O-DisCo-Edit.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01596 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing Chen, Yuqing Wang, Junjie Liu, Lin Chu, Ruihang Zhang, Xiaopeng Tian, Qi Yang, Yujiu Computer Vision and Pattern Recognition Artificial Intelligence Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current methods require different control signal for diverse editing tasks, which complicates model design and demands significant training resources. To address this, we propose O-DisCo-Edit, a unified framework that incorporates a novel object distortion control (O-DisCo). This signal, based on random and adaptive noise, flexibly encapsulates a wide range of editing cues within a single representation. Paired with a "copy-form" preservation module for preserving non-edited regions, O-DisCo-Edit enables efficient, high-fidelity editing through an effective training paradigm. Extensive experiments and comprehensive human evaluations consistently demonstrate that O-DisCo-Edit surpasses both specialized and multitask state-of-the-art methods across various video editing tasks. https://cyqii.github.io/O-DisCo-Edit.github.io/ |
| title | O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.01596 |