DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming

2026-09-15

AI Summary

DecoGS通过选择性优化动态区域，解决3D重建中速度与时间保真度的平衡问题，实现高效无闪烁的自由视角视频流。

Abstract

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.

Problem

• 3D Reconstruction
• Streaming Videos
• Temporal Fidelity
• Gaussian Updates
• Static Regions

Innovation

• Adaptive Mechanism
• Spatiotemporal Region Optimization
• Gradient Gating
• Visibility Filtering
• Temporal Coherence