FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917349511135232 |
|---|---|
| author | Wang, Zhen Xu, Youcan Xiao, Jun Chen, Long |
| author_facet | Wang, Zhen Xu, Youcan Xiao, Jun Chen, Long |
| contents | Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of pre-trained T2V models, which results in heavy computational overhead and limited flexibility. In this paper, we present FlowMotion, a novel training-free framework that enables efficient and flexible motion transfer by directly leveraging the predicted outputs of flow-based T2V models. Our key insight is that early latent predictions inherently encode rich temporal information. Motivated by this, we propose flow guidance, which extracts motion representations based on latent predictions to align motion patterns between source and generated videos. We further introduce a velocity regularization strategy to stabilize optimization and ensure smooth motion evolution. By operating purely on model predictions, FlowMotion achieves superior time and resource efficiency as well as competitive performance compared with state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06289 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowMotion: Training-Free Flow Guidance for Video Motion Transfer Wang, Zhen Xu, Youcan Xiao, Jun Chen, Long Computer Vision and Pattern Recognition Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of pre-trained T2V models, which results in heavy computational overhead and limited flexibility. In this paper, we present FlowMotion, a novel training-free framework that enables efficient and flexible motion transfer by directly leveraging the predicted outputs of flow-based T2V models. Our key insight is that early latent predictions inherently encode rich temporal information. Motivated by this, we propose flow guidance, which extracts motion representations based on latent predictions to align motion patterns between source and generated videos. We further introduce a velocity regularization strategy to stabilize optimization and ensure smooth motion evolution. By operating purely on model predictions, FlowMotion achieves superior time and resource efficiency as well as competitive performance compared with state-of-the-art methods. |
| title | FlowMotion: Training-Free Flow Guidance for Video Motion Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.06289 |