EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation

Jiahao Wu, Jie Liang, Die Hu, Jiayu Yang, Kaiqiang Xiong, Xiang Li, Xiaoyun Zheng, Chao Wang, Ronggang Wang

ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-13

DOI: 10.1145/3811306 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Jiahao Wu und 8 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China, Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Outstanding Talents Training Fund in Shenzhen, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose ATGS, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that ATGS consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

Förderung

  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
  • Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology
  • Outstanding Talents Training Fund in Shenzhen, Shenzhen Science and Technology Program

Zitieren

APA

Wu, J., Liang, J., Hu, D., Yang, J., Xiong, K., Li, X., Zheng, X., Wang, C., & Wang, R. (2026). ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation. ACM Transactions on Graphics, 45(4), 1-13. https://doi.org/10.1145/3811306

Vancouver

Wu J, Liang J, Hu D, Yang J, Xiong K, Li X, et al. ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation. ACM Transactions on Graphics. 2026;45(4):1-13. doi:10.1145/3811306

BibTeX
@article{Wu2026,
  author = {Wu, Jiahao and Liang, Jie and Hu, Die and Yang, Jiayu and Xiong, Kaiqiang and Li, Xiang and Zheng, Xiaoyun and Wang, Chao and Wang, Ronggang},
  title = {ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {4},
  pages = {1--13},
  doi = {10.1145/3811306}
}
Kostenlos starten →