Research map / 3D vision / Gaussian splatting
ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
Jie Liang, Jiahao Wu, Chao Wang, Jiayu Yang, Xiaoyun Zheng, Kaiqiang Xiong, Zhanke Wang, Jinbo Yan, Feng Gao, Ronggang Wang
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 decoder inheritance from the Reference Clip (ablation) | ClipGStream · Long 360 (1400 frames) | PSNR: 24.34 -> 24.54 | Improved |
| add decoder inheritance from the Reference Clip (ablation) | ClipGStream · Long 360 (1400 frames) | LPIPS: 0.152 -> 0.146 | Improved |
| add residual anchors compensation (RAC) (ablation) | ClipGStream · Long 360 (1400 frames) | PSNR: 23.62 -> 24.54 | Improved |
| add residual anchors compensation (RAC) (ablation) | ClipGStream · Long 360 (1400 frames) | LPIPS: 0.160 -> 0.146 | Improved |
| use clip-specific spatio-temporal fields instead of one shared STF (ablation) | ClipGStream · Long 360 (1400 frames) | PSNR: 23.11 -> 24.54 | Improved |
| use clip-specific spatio-temporal fields instead of one shared STF (ablation) | ClipGStream · Long 360 (1400 frames) | LPIPS: 0.178 -> 0.146 | Improved |
| add inter-clip inheritance instead of training clips independently (ablation) | ClipGStream · Long 360 (1400 frames) | PSNR: 21.85 -> 24.54 | Improved |
| add inter-clip inheritance instead of training clips independently (ablation) | ClipGStream · Long 360 (1400 frames) | LPIPS: 0.316 -> 0.146 | Improved |
| add anchors inheritance (freeze reference anchors and static features) (ablation) | ClipGStream · Long 360 (1400 frames) | flicker (qualitative) | Improved |
| use Clip-Stream framework instead of Clip method LocalDyGS | ClipGStream · Long 360 (1400 frames) | PSNR: 23.11 -> 24.54 | Improved |
| use Clip-Stream framework instead of Clip method LocalDyGS | ClipGStream · N3DV (five 300-frame scenes) | PSNR: 32.28 -> 32.53 | Improved |
| use Clip-Stream framework instead of Clip method LocalDyGS | ClipGStream · N3DV flame salmon (1200 frames) | PSNR: 28.15 -> 29.40 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- LocalDyGS — LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling (ICCV 2025) · better on 6 of 6 shared results
- Swift4D — Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025) · better on 2 of 2 shared results
- 3DGStream — 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024) · better on 2 of 2 shared results
- ScaffoldGS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 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
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.90)
- Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting (CVPR 2025 · similarity 0.90)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.89)
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.89)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.88)
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.
