Research map / 3D vision / Gaussian splatting
StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video
Zhihui Ke, Yvyang Liu, Xiaobo Zhou, Tie Qiu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Transformer-guided auxiliary training (ablation) | StreamSTGS · N3DV | PSNR (dB): 31.99 -> 32.30 | Improved |
| add dynamic-aware density (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.07 -> 32.30 | Improved |
| add temporal consistency regularization (ablation) | StreamSTGS · N3DV | storage (KB): 319.48 -> 173.59 | Improved |
| add temporal consistency regularization (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.23 -> 32.30 | No clear effect |
| add Gaussian relocate (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.11 -> 32.30 | Improved |
| use sliding window W=3 instead of W=1 (ablation) | StreamSTGS · N3DV | storage (KB): 298.06 -> 173.59 | Improved |
| increase sliding window from 3 to 5 (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.30 -> 32.26 | No clear effect |
| increase GOP length from 30 to 100 (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.32 -> 32.06 | Hurt |
| increase GOP length from 30 to 100 (ablation) | StreamSTGS · N3DV | storage (KB): 228.7 -> 161.9 | Improved |
| raise HEVC compression QP from 16 to 32 (ablation) | StreamSTGS · N3DV | PSNR (dB): 32.36 -> 30.76 | Hurt |
| use StreamSTGS instead of iFVC | FVV streaming · N3DV | LPIPS: 0.136 vs 0.147 | Hurt |
| use StreamSTGS instead of 4DGC | FVV streaming · N3DV | PSNR (dB): 31.52 -> 32.30 | Improved |
Later papers that compared with this method
1 later accepted paper reports StreamSTGS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming (ECCV 2026 · better on 2 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- 3DGStream — 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024) · better on 1 of 1 shared result
- HiCoM — HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024 · similarity 0.94)
- Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting (CVPR 2025 · similarity 0.93)
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.93)
- Compressing Streamable Free-Viewpoint Videos to 0.1 MB per Frame (AAAI 2025 · similarity 0.91)
- 4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video (CVPR 2025 · similarity 0.91)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
