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

• URL: http://arxiv.org/abs/2609.17230v1
• Date: Tue, 15 Sep 2026 14:12:16 GMT
• Title: DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming
• Abstract summary: 3D reconstruction demands both speed and temporal fidelity.<n>We present DecoGS, a method for efficient online training of 3D flickers from streaming videos.
• Score: 5.9964446074327995
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization [54.179316928687435]
  TurboGS is an error-guided training framework that accelerates 3DGS by concentrating optimization on perceptually informative pixels.<n>Experiments on standard benchmarks demonstrate that TurboGS can deliver on par or superior rendering quality within 100 seconds on a single 5090 GPU card.
  arXiv  Detail & Related papers  (2026-06-14T16:59:48Z)
• WorldCache: Content-Aware Caching for Accelerated Video World Models [50.7543797435026]
  We present textbfWorldCache, a Perception-Constrained Dynamic CaCache framework.<n>WorldCache improves both when and how to reuse features.<n>On Cosmos-2.5-2B evaluated on PAI-Bench, WorldCache achieves textbf$2.3times$ inference speedup while preserving textbf99.4% of baseline quality.
  arXiv  Detail & Related papers  (2026-03-23T17:59:54Z)
• AirGS: Real-Time 4D Gaussian Streaming for Free-Viewpoint Video Experiences [8.988150010963382]
  Free-viewpoint video (FVV) enables immersive viewing experiences by allowing users to view scenes from arbitrary perspectives.<n>We present AirGS, a streaming-optimized 4DGS framework that rearchitects the training and delivery to enable high-quality, low-latency experiences.
  arXiv  Detail & Related papers  (2025-12-24T04:57:30Z)
• StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video [16.890908589888678]
  Streaming free-viewpoint video(FVV) in real-time faces significant challenges.<n>Recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering.<n>We propose a novel FVV representation, dubbed StreamSTGS, designed for real-time streaming.
  arXiv  Detail & Related papers  (2025-11-08T15:35:43Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction [5.818188539758898]
  We present SD-GS, a compact and efficient dynamic splatting framework for complex dynamic scene reconstruction.<n>We also present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions.<n> Experimental results demonstrate that SD-GS achieves an average of 60% reduction in model size and an average of 100% improvement in FPS.
  arXiv  Detail & Related papers  (2025-07-10T06:35:03Z)
• Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes [57.69608119350651]
  Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian.<n>However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements.<n>We present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques.
  arXiv  Detail & Related papers  (2025-06-09T16:30:48Z)
• VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment [54.66217340264935]
  VideoLifter is a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis.<n>It significantly accelerates the reconstruction process, reducing training time by over 82% while holding better visual quality than current SOTA methods.
  arXiv  Detail & Related papers  (2025-01-03T18:52:36Z)
• Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives [60.217580865237835]
  3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians.<n>We identify and address two key inefficiencies in 3D-GS to substantially improve rendering speed.<n>Our Speedy-Splat approach combines these techniques to accelerate average rendering speed by a drastic $mathit6.71times$ across scenes from the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets.
  arXiv  Detail & Related papers  (2024-11-30T20:25:56Z)
• Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
  We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.<n>We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling.<n>We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T08:23:38Z)
• Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction [15.588032729272536]
  Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians.<n>We propose a novel three-stage pipeline for iterative streamable 4D dynamic spatial reconstruction.<n>Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating the fastest on-the-fly training, superior representation quality, and real-time rendering capability.
  arXiv  Detail & Related papers  (2024-11-22T10:47:47Z)
• 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos [10.323643152957114]
  3DGStream is a method designed for efficient FVV streaming of real-world dynamic scenes. Our method achieves fast on-the-fly per-frame reconstruction within 12 seconds and real-time rendering at 200 FPS.
  arXiv  Detail & Related papers  (2024-03-03T08:42:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.