Research map / 3D vision / Gaussian splatting
Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians
Guangchi Fang, Bing 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 blur split and depth reinitialization (Mini-Splatting-D densification) (ablation) | 3DGS · Mip-NeRF360 | LPIPS: 0.216 -> 0.175 | Improved |
| Add blur split to baseline 3DGS (ablation) | 3DGS · Mip-NeRF360 | PSNR: 27.47 -> 27.47 | No clear effect |
| Reinitialize with alpha-blended depth instead of mid-point depth (ablation) | Mini-Splatting-D · Mip-NeRF360 | PSNR: 27.54 -> 17.67 | Hurt |
| Use Gaussian center depth instead of mid-point depth (ablation) | Mini-Splatting-D · Mip-NeRF360 | PSNR: 27.54 -> 27.57 | No clear effect |
| Add intersection preserving and importance-weighted sampling instead of direct pruning (ablation) | Mini-Splatting-D · Mip-NeRF360 | quality vs number of Gaussians | Improved |
| Prune 3DGS directly from 6.1M to 0.6M Gaussians (ablation) | 3DGS · Mip-NeRF360 (single scene) | PSNR: 25.2 -> 24.9 dB | Hurt |
| Simplify to 0.49M Gaussians with Mini-Splatting | Mini-Splatting-D · Mip-NeRF360 | rendering FPS (outdoor): 98 -> 410 | Improved |
| Apply depth-based reinitialization on scenes with large sky | Mini-Splatting · Tanks&Temples | PSNR: 23.66 -> 23.18 | Hurt |
| Initialize with dense MVS points instead of sparse SfM (ablation) | 3DGS · Mip-NeRF360 | LPIPS: 0.216 -> 0.180 | Improved |
| Dense initialization for Mini-Splatting-D (ablation) | Mini-Splatting-D · Mip-NeRF360 | PSNR: 27.54 -> 27.76 | No clear effect |
Later papers that compared with this method
14 later accepted papers report Mini-Splatting as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.
- GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting (CVPR 2026 · better on 4 of 5 shared results)
- LiteGS: a high-performance framework to train 3dgs in subminutes via system and algorithm codesign (ECCV 2026 · better on 4 of 4 shared results)
- Gradient-Direction-Aware Density Control for 3D Gaussian Splatting (ICLR 2026 · better on 2 of 3 shared results)
- Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior (ECCV 2026 · better on 1 of 3 shared results)
- TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization (ICML 2026 · better on 2 of 2 shared results)
- AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting (NeurIPS 2026 · better on 2 of 2 shared results)
- FastGS: Training 3D Gaussian Splatting in 100 Seconds (CVPR 2026 · better on 2 of 2 shared results)
- Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices (CVPR 2026 · better on 2 of 2 shared results)
6 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · 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 0.92)
- Lightweight Predictive 3D Gaussian Splats (ICLR 2025 · similarity 0.92)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.91)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 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.
