Research
DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming
arXiv:2609.17230v1 Announce Type: new Abstract: Streaming 3D reconstruction demands both speed and temporal fidelity, goals that existing methods undermine by updating every Gaussian every frame, even
arXiv:2609.17230v1 Announce Type: new 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 70imes lower temporal flicker than the best prior method, requiring no large-scale pretraining.
Related
- DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming
- SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
- STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation
- CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
- Decoupling Motion and Geometry in 4D Gaussian Splatting
Source: arXiv cs.CV | 2026-09-16