发表机构
Shenzhen Graduate School, Peking University; Pengcheng Laboratory（北京大学深圳研究生院; 鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长序列体积视频的时间不稳定问题，提出基于高斯溅射的ATGS框架，通过时间条件锚点组织高斯、时间窗口策略及多级锚点特征约束，实现更优的长序列体积视频重建性能。
AI 中文摘要
体积视频可实现对真实世界动态场景的沉浸式自由视点渲染，但现有方法在处理长序列和复杂运动时存在困难，常导致时间不稳定和视觉伪影。为应对这些挑战，我们提出ATGS，一种基于高斯溅射的体积视频重建框架。我们的核心见解是，用单个高斯基元显式跟踪长期复杂运动本质上不稳定，因此我们围绕时间条件锚点组织高斯，锚点定位其空间和时间支撑，从而降低长程运动复杂性。我们进一步引入时间窗口策略，仅激活与查询时间相关的锚点，这提升了可扩展性和时间一致性。此外，为确保空间和时间稳定性，我们设计了一组紧凑的多级锚点特征，其编码全局特征、局部空间特征和局部时间特征，共同约束高斯生成。大量实验表明，ATGS在含复杂运动的长序列体积视频上始终优于现有方法。项目页面：this https URL。
英文摘要
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.
CommentsACM ToG(SIGGRAPH'2026)
