VIDMP3: Video Editing by Representing Motion with Pose and Position Priors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908591550627840 |
|---|---|
| author | Mishra, Sandeep Saha, Oindrila Bovik, Alan C. |
| author_facet | Mishra, Sandeep Saha, Oindrila Bovik, Alan C. |
| contents | Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing diffusion-based editing methods excel in structure-preserving tasks, using dense guidance signals to ensure content integrity. While some recent methods attempt to address structure-variable editing, they often suffer from issues such as temporal inconsistency, subject identity drift, and the need for human intervention. To address these challenges, we introduce VidMP3, a novel approach that leverages pose and position priors to learn a generalized motion representation from source videos. Our method enables the generation of new videos that maintain the original motion while allowing for structural and semantic flexibility. Both qualitative and quantitative evaluations demonstrate the superiority of our approach over existing methods. The code will be made publicly available at https://github.com/sandeep-sm/VidMP3. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12069 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VIDMP3: Video Editing by Representing Motion with Pose and Position Priors Mishra, Sandeep Saha, Oindrila Bovik, Alan C. Computer Vision and Pattern Recognition Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing diffusion-based editing methods excel in structure-preserving tasks, using dense guidance signals to ensure content integrity. While some recent methods attempt to address structure-variable editing, they often suffer from issues such as temporal inconsistency, subject identity drift, and the need for human intervention. To address these challenges, we introduce VidMP3, a novel approach that leverages pose and position priors to learn a generalized motion representation from source videos. Our method enables the generation of new videos that maintain the original motion while allowing for structural and semantic flexibility. Both qualitative and quantitative evaluations demonstrate the superiority of our approach over existing methods. The code will be made publicly available at https://github.com/sandeep-sm/VidMP3. |
| title | VIDMP3: Video Editing by Representing Motion with Pose and Position Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.12069 |