Research map / 3D vision / Gaussian splatting
StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
Yang Li, Jinglu Wang, Lei Chu, Xiao Li, Shiu-Hong Kao, Ying-Cong Chen, Yan Lu
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 joint refinement of cameras and Gaussian centers (ablation) | StreamGS · RE10K | PSNR: 17.25 -> 22.42 | Improved |
| add joint refinement of cameras and Gaussian centers (ablation) | StreamGS · ACID | PSNR: 17.23 -> 28.50 | Improved |
| add joint refinement of cameras and Gaussian centers (ablation) | StreamGS · RE10K | LPIPS: 0.32 -> 0.17 | Improved |
| add joint refinement of cameras and Gaussian centers (ablation) | StreamGS · ACID | SSIM: 0.48 -> 0.84 | Improved |
| add Gaussian merging in feed-forward ADC (ablation) | StreamGS · MVImgNet | PSNR: 25.70 -> 25.05 | Hurt |
| add Gaussian merging in feed-forward ADC (ablation) | StreamGS · ACID | PSNR: 29.21 -> 28.07 | Hurt |
| add Gaussian merging in feed-forward ADC (ablation) | StreamGS · MVImgNet | compression ratio: 1.00 -> 1.58 | Improved |
| add Gaussian merging in feed-forward ADC (ablation) | StreamGS · ACID | compression ratio: 1.00 -> 1.68 | Improved |
| use matched Gaussian pairs across adjacent frames rather than random pairs | cross-frame Gaussian matching · RE10K | opacity difference: 0.10 -> 0.04 | Improved |
| StreamGS versus MVSplat on out-of-domain MVImgNet | StreamGS · MVImgNet | PSNR: 16.29 -> 25.05 | Improved |
| StreamGS versus MVSplat on source domain RE10K | StreamGS · RE10K | PSNR: 23.54 -> 22.42 | Hurt |
| StreamGS versus CF-GS on ScanNet | StreamGS · ScanNet | PSNR: 22.88 -> 28.43 | Improved |
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.
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 6 of 10 shared results
- pixelSplat — pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024) · better on 3 of 5 shared results
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
- Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting (CVPR 2025 · similarity 0.92)
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.92)
- Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting (ICLR 2025 · similarity 0.91)
- SpikeGS: Reconstruct 3D Scene Captured by a Fast-Moving Bio-Inspired Camera (AAAI 2025 · similarity 0.91)
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.91)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
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.
