Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2604.03310 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914444858097664 |
|---|---|
| author | Wang, Haichao Okupnik, Alexander Han, Yuxing Wen, Gene Schneider, Johannes Flouris, Kyriakos |
| author_facet | Wang, Haichao Okupnik, Alexander Han, Yuxing Wen, Gene Schneider, Johannes Flouris, Kyriakos |
| contents | Long-range human movement generation remains a central challenge in computer vision and graphics. Generating coherent transitions across semantically distinct motion domains remains largely unexplored. This capability is particularly important for applications such as dance choreography, where movements must fluidly transition across diverse stylistic and semantic motifs. We propose a simple and effective inference-time optimization framework inspired by diffusion-based stochastic optimal control. Specifically, a control-energy objective that explicitly regularizes the transition trajectories of a pretrained diffusion model. We show that optimizing this objective at inference time yields transitions with fidelity and temporal coherence. This is the first work to provide a general framework for controlled long-range human motion generation with explicit transition modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03310 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions Wang, Haichao Okupnik, Alexander Han, Yuxing Wen, Gene Schneider, Johannes Flouris, Kyriakos Computer Vision and Pattern Recognition Long-range human movement generation remains a central challenge in computer vision and graphics. Generating coherent transitions across semantically distinct motion domains remains largely unexplored. This capability is particularly important for applications such as dance choreography, where movements must fluidly transition across diverse stylistic and semantic motifs. We propose a simple and effective inference-time optimization framework inspired by diffusion-based stochastic optimal control. Specifically, a control-energy objective that explicitly regularizes the transition trajectories of a pretrained diffusion model. We show that optimizing this objective at inference time yields transitions with fidelity and temporal coherence. This is the first work to provide a general framework for controlled long-range human motion generation with explicit transition modeling. |
| title | Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.03310 |