ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation

2026-08-30

AI Summary

为解决长序列体三维视频中复杂运动导致的不稳定性和视觉伪影问题，提出基于高斯点云的ATGS框架，通过时间锚点和多级特征编码提升时空稳定性和一致性。

Abstract

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 \ourname, 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 \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

Problem

• volumetric video
• temporal instability
• visual artifacts

Innovation

• Anchored Temporal Gaussian Splatting
• volumetric video reconstruction
• time conditioned anchors
• temporal windowing strategy
• multi-level anchor features