Point-to-Point: Sparse Motion Guidance for Controllable Video Editing
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_ | 1866915634530484224 |
|---|---|
| author | Song, Yeji Lee, Jaehyun Koo, Mijin Lee, JunHoo Kwak, Nojun |
| author_facet | Song, Yeji Lee, Jaehyun Koo, Mijin Lee, JunHoo Kwak, Nojun |
| contents | Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either overfitted to the layout or only implicitly defined. To overcome this limitation, we revisit point-based motion representation. However, identifying meaningful points remains challenging without human input, especially across diverse video scenarios. To address this, we propose a novel motion representation, anchor tokens, that capture the most essential motion patterns by leveraging the rich prior of a video diffusion model. Anchor tokens encode video dynamics compactly through a small number of informative point trajectories and can be flexibly relocated to align with new subjects. This allows our method, Point-to-Point, to generalize across diverse scenarios. Extensive experiments demonstrate that anchor tokens lead to more controllable and semantically aligned video edits, achieving superior performance in terms of edit and motion fidelity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Point-to-Point: Sparse Motion Guidance for Controllable Video Editing Song, Yeji Lee, Jaehyun Koo, Mijin Lee, JunHoo Kwak, Nojun Computer Vision and Pattern Recognition Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either overfitted to the layout or only implicitly defined. To overcome this limitation, we revisit point-based motion representation. However, identifying meaningful points remains challenging without human input, especially across diverse video scenarios. To address this, we propose a novel motion representation, anchor tokens, that capture the most essential motion patterns by leveraging the rich prior of a video diffusion model. Anchor tokens encode video dynamics compactly through a small number of informative point trajectories and can be flexibly relocated to align with new subjects. This allows our method, Point-to-Point, to generalize across diverse scenarios. Extensive experiments demonstrate that anchor tokens lead to more controllable and semantically aligned video edits, achieving superior performance in terms of edit and motion fidelity. |
| title | Point-to-Point: Sparse Motion Guidance for Controllable Video Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.18277 |