Research map / 3D vision / Gaussian splatting
FastGS: Training 3D Gaussian Splatting in 100 Seconds
Shiwei Ren, Tianci Wen, Yongchun Fang, Biao 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 multi-view consistent densification (VCD) (ablation) | 3DGS-accel · Mip-NeRF 360 | training time: 7.10 -> 3.53 min; Gaussians 2.64M -> 0.53M | Improved |
| add VCD (ablation) | 3DGS-accel · Mip-NeRF 360 | SSIM/LPIPS: SSIM 0.810 -> 0.798; LPIPS 0.226 -> 0.259; PSNR 27.46 -> 27.69 | Mixed |
| add multi-view consistent pruning (VCP) (ablation) | 3DGS-accel · Mip-NeRF 360 | training time: 7.10 -> 5.32 min; Gaussians 2.64M -> 1.96M | Improved |
| add compact box (CB) (ablation) | 3DGS-accel · Mip-NeRF 360 | training time: 7.10 -> 6.13 min | Improved |
| combine VCD, VCP and CB (ablation) | 3DGS-accel · Mip-NeRF 360 | training time: 7.10 -> 1.93 min | Improved |
| FastGS-Big instead of DashGaussian | DashGaussian · Mip-NeRF 360 | PSNR / time: 27.73 -> 27.93 dB; 6.35 -> 3.58 min | Improved |
| FastGS instead of Taming-3DGS | Taming-3DGS · Mip-NeRF 360 | training time: 5.36 -> 1.93 min | Improved |
| plug FastGS into Deformable-3DGS | Deformable-3DGS · Neu3D | training time: 26.16 -> 9.29 min; PSNR 26.74 -> 29.29 | Improved |
| plug FastGS into PGSR | PGSR · Tanks & Temples (surface) | LPIPS/F1: time 32.28 -> 15.74; LPIPS 0.149 -> 0.190; F1 0.57 -> 0.55 | Mixed |
| plug FastGS into Scaffold-GS | Scaffold-GS · Mip-NeRF 360 | training time: 18.37 -> 5.06 min | 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.
- Speedy-splat — Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025) · better on 2 of 2 shared results
- Mini-Splatting — Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians (ECCV 2024) · better on 2 of 2 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
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.95)
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering (CVPR 2025 · similarity 0.94)
- FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting (CVPR 2025 · similarity 0.94)
- LP-3DGS: Learning to Prune 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.93)
- HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting (CVPR 2025 · similarity 0.93)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.93)
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.
