Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (14) · 11469-11477
DOI: 10.1609/aaai.v40i14.38129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhixin Xu und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Multi-view video reconstruction plays a vital role in computer vision, enabling applications in film production, virtual reality, and motion analysis. While recent advances such as 3D Gaussian Splatting have demonstrated impressive capabilities in dynamic scene reconstruction, they typically rely on the assumption that input video streams are temporally synchronized. However, in real-world scenarios, this assumption often fails due to factors like camera trigger delays, frame rate discrepancies, or independent recording setups, leading to temporal misalignment across views and reduced reconstruction quality. To address this challenge, a novel temporal alignment strategy is proposed for high-quality 4DGS reconstruction from unsynchronized multi-view videos. Our method features a coarse-to-fine alignment module that estimates and compensates for each camera's time shift. The method first determines a coarse, frame-level offset and then refines it to achieve sub-frame accuracy. This strategy can be integrated as a plug-and-play module into existing 4DGS frameworks, enhancing their robustness when handling asynchronous data. Experiments show that this approach effectively processes temporally misaligned videos and significantly enhances baseline methods.
Zitieren
APA
Xu, Z., Zhou, H., Liu, Y., Xue, W., Pan, H., Wang, W., & Wang, B. (2026). Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 40(14), 11469-11477. https://doi.org/10.1609/aaai.v40i14.38129
Vancouver
Xu Z, Zhou H, Liu Y, Xue W, Pan H, Wang W, et al. Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(14):11469-11477. doi:10.1609/aaai.v40i14.38129
BibTeX
@article{Xu2026,
author = {Xu, Zhixin and Zhou, Hengyu and Liu, Yuan and Xue, Wenhan and Pan, Hao and Wang, Wenping and Wang, Bin},
title = {Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {14},
pages = {11469--11477},
doi = {10.1609/aaai.v40i14.38129}
}
EUVIMED