Research map / 3D vision / Gaussian splatting
Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
Jiaqi Liu, Zhizhong Han
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 scale reset (ablation) | LiteGS · Mip-NeRF 360 | training time (s): 191.17 -> 147.33 | Improved |
| add scale reset (ablation) | LiteGS · Mip-NeRF 360 | PSNR: 27.75 -> 27.33 | Hurt |
| add entropy constraint (ablation) | LiteGS · Mip-NeRF 360 | training time (s): 191.17 -> 162.53 | Improved |
| add entropy constraint (ablation) | LiteGS · Mip-NeRF 360 | PSNR: 27.75 -> 27.35 | Hurt |
| add scale reset and entropy to LiteGS+DashGaussian (ablation) | LiteGS+DashGaussian · Mip-NeRF 360 | training time (s): 134.99 -> 99.58 | Improved |
| add scale reset and entropy to LiteGS+DashGaussian (ablation) | LiteGS+DashGaussian · Mip-NeRF 360 | PSNR: 27.85 -> 27.28 | Hurt |
| replace volume regularization with scale reset (ablation) | L+D+E · Mip-NeRF 360 | training time (s): 107.91 -> 99.58 | Improved |
| replace volume regularization with scale reset (ablation) | L+D+E · Mip-NeRF 360 | PSNR: 27.17 -> 27.28 | Improved |
| replace opacity loss with entropy constraint (ablation) | L+D+R · Mip-NeRF 360 | training time (s): 106.16 -> 99.58 | Improved |
| replace opacity loss with entropy constraint (ablation) | L+D+R · Mip-NeRF 360 | PSNR: 27.29 -> 27.28 | No clear effect |
| shrink more aggressively (zeta 0.2 -> 0.1) (ablation) | scale reset · Mip-NeRF 360 | training time (s): 99.58 -> 98.34 | Improved |
| shrink more aggressively (zeta 0.2 -> 0.1) (ablation) | scale reset · Mip-NeRF 360 | PSNR: 27.28 -> 27.14 | Hurt |
Closest papers by meaning
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.93)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 2025 · similarity 0.92)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.92)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering (CVPR 2024 · similarity 0.92)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.92)
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.
