PanFlow: Decoupled Motion Control for Panoramic Video Generation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12385-12393
DOI: 10.1609/aaai.v40i15.38231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Cheng Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Zhang, C., Liang, H., Chen, D. Y., Wu, Q., Plataniotis, K. N., Gambardella, C. C., & Cai, J. (2026). PanFlow: Decoupled Motion Control for Panoramic Video Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12385-12393. https://doi.org/10.1609/aaai.v40i15.38231
Vancouver
Zhang C, Liang H, Chen DY, Wu Q, Plataniotis KN, Gambardella CC, et al. PanFlow: Decoupled Motion Control for Panoramic Video Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12385-12393. doi:10.1609/aaai.v40i15.38231
BibTeX
@article{Zhang2026,
author = {Zhang, Cheng and Liang, Hanwen and Chen, Donny Y. and Wu, Qianyi and Plataniotis, Konstantinos N. and Gambardella, Camilo Cruz and Cai, Jianfei},
title = {PanFlow: Decoupled Motion Control for Panoramic Video Generation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {15},
pages = {12385--12393},
doi = {10.1609/aaai.v40i15.38231}
}
EUVIMED