PanFlow: Decoupled Motion Control for Panoramic Video Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908682053222400 |
|---|---|
| author | Zhang, Cheng Liang, Hanwen Chen, Donny Y. Wu, Qianyi Plataniotis, Konstantinos N. Gambardella, Camilo Cruz Cai, Jianfei |
| author_facet | Zhang, Cheng Liang, Hanwen Chen, Donny Y. Wu, Qianyi Plataniotis, Konstantinos N. Gambardella, Camilo Cruz Cai, Jianfei |
| contents | Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions. We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries. To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations. We also showcase the effectiveness of our method in various applications, including motion transfer and video editing. Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence. Our code, dataset, and models are available at https://github.com/chengzhag/PanFlow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00832 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PanFlow: Decoupled Motion Control for Panoramic Video Generation Zhang, Cheng Liang, Hanwen Chen, Donny Y. Wu, Qianyi Plataniotis, Konstantinos N. Gambardella, Camilo Cruz Cai, Jianfei Computer Vision and Pattern Recognition Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions. We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries. To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations. We also showcase the effectiveness of our method in various applications, including motion transfer and video editing. Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence. Our code, dataset, and models are available at https://github.com/chengzhag/PanFlow. |
| title | PanFlow: Decoupled Motion Control for Panoramic Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.00832 |