EUVIMEDEUVIMED entdecken
Crossref

Cross-temporal 3D Gaussian Splatting for Sparse-view Guided Scene Update

Zeyuan An, Yanghang Xiao, Zhiying Leng, Frederick W. B. Li, Xiaohui Liang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2327-2335

DOI: 10.1609/aaai.v40i4.37217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zeyuan An und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster assessment, and historical site preservation, where dense scans are often unavailable or impractical. In this paper, we propose Cross-Temporal 3D Gaussian Splatting (Cross-Temporal 3DGS), a novel framework for efficiently reconstructing and updating 3D scenes across different time periods, using sparse images and previously captured scene priors. Our approach comprises three stages: 1) Cross-temporal camera alignment for estimating and aligning camera poses across different timestamps; 2) Interference-based confidence initialization to identify unchanged regions between timestamps, thereby guiding updates; and 3) Progressive cross-temporal optimization, which iteratively integrates historical prior information into the 3D scene to enhance reconstruction quality. Our method supports non-continuous capture, enabling not only updates using new sparse views to refine existing scenes, but also recovering past scenes from limited data with the help of current captures. Furthermore, we demonstrate the potential of this approach to achieve temporal changes using only sparse images, which can later be reconstructed into detailed 3D representations as needed. Experimental results show significant improvements over baseline methods in reconstruction quality and data efficiency, making this approach a promising solution for scene versioning, cross-temporal digital twins, and long-term spatial documentation.

Zitieren

APA

An, Z., Xiao, Y., Leng, Z., Li, F. W. B., & Liang, X. (2026). Cross-temporal 3D Gaussian Splatting for Sparse-view Guided Scene Update. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2327-2335. https://doi.org/10.1609/aaai.v40i4.37217

Vancouver

An Z, Xiao Y, Leng Z, Li FWB, Liang X. Cross-temporal 3D Gaussian Splatting for Sparse-view Guided Scene Update. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2327-2335. doi:10.1609/aaai.v40i4.37217

BibTeX
@article{An2026,
  author = {An, Zeyuan and Xiao, Yanghang and Leng, Zhiying and Li, Frederick W. B. and Liang, Xiaohui},
  title = {Cross-temporal 3D Gaussian Splatting for Sparse-view Guided Scene Update},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2327--2335},
  doi = {10.1609/aaai.v40i4.37217}
}
Kostenlos starten →