DecoGS：面向自由视角视频流的三维高斯自适应静态-动态解耦
DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming
- University of Bonn（波恩大学）
- Almetra
- V3DEO
- Cauth AI
- Intel Labs（英特尔实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
DecoGS通过自适应静态-动态解耦，选择性优化运动区域，实现流式三维高斯的高效在线训练，在N3DV和MeetRoom上达到最优PSNR，并以低70倍闪烁和261 FPS渲染。
AI中文摘要：
流式三维重建要求兼具速度与时间保真度，而现有方法通过逐帧更新每个高斯（即使在静态区域）来破坏这些目标。我们提出DecoGS，一种从流式视频中高效在线训练三维高斯的方法。与先前不加区分地更新整个场景的方法不同，DecoGS引入自适应机制，选择性地将优化聚焦于表现出运动或光度变化的时空区域。这种有针对性的训练策略消除了在名义静态区域中导致闪烁和漂移的冗余更新，同时实现快速、高保真的场景更新。该流程进一步通过梯度门控和高效可见性过滤整合区域感知的高斯管理，以维持时间连贯性和紧凑的内存占用。在N3DV和MeetRoom上，DecoGS分别达到34.55和31.60 dB的PSNR，优于所有流式和离线基线，同时以261 FPS渲染，时间闪烁比最佳先前方法低70倍，且无需大规模预训练。
英文摘要：
Streaming 3D reconstruction demands both speed and temporal fidelity, goals that existing methods undermine by updating every Gaussian every frame, even in static regions. We present DecoGS, a method for efficient online training of 3D Gaussians from streaming videos. Unlike prior methods that update the entire scene indiscriminately, DecoGS introduces an adaptive mechanism that selectively focuses optimization on spatiotemporal regions exhibiting motion or photometric changes. This targeted training strategy eliminates redundant updates that cause flickering and drift in nominally static regions, while enabling fast, high-fidelity scene updates. The pipeline further integrates region-aware Gaussian management through gradient gating and efficient visibility filtering to maintain temporal coherence and a compact memory footprint. On N3DV and MeetRoom, DecoGS achieves 34.55 and 31.60 dB PSNR respectively, outperforming all streaming and offline baselines, while rendering at 261 FPS with $70\times$ lower temporal flicker than the best prior method, requiring no large-scale pretraining.
