Research map / 3D vision / Gaussian splatting
Pushing Rendering Boundaries: Hard Gaussian Splatting
Qingshan Xu, Jiequan Cui, Xuanyu Yi, Yuxuan Wang, Yuan Zhou, Yew-Soon Ong, Hanwang Zhang
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 positional gradient driven HGS (PGHGS) (ablation) | Scaffold-GS · Tanks&Temples | LPIPS: 0.170 -> 0.129 | Improved |
| add rendering error guided HGS (REHGS) (ablation) | Scaffold-GS · Tanks&Temples | LPIPS: 0.170 -> 0.155 | Improved |
| add REHGS on top of PGHGS (ablation) | Model-A · Tanks&Temples | LPIPS: 0.129 -> 0.126 | Improved |
| add Effi-HGS to existing Gaussian methods | 3DGS, Pixel-GS*, Mip-Splatting*, HAC · Tanks&Temples | LPIPS: HAC 0.173 -> 0.150; 3DGS 0.178 -> 0.163 | Improved |
| replace Scaffold-GS growing with full HGS | Scaffold-GS · Mip-NeRF360 | PSNR: 27.98 -> 28.30 | Improved |
| replace Scaffold-GS growing with full HGS | Scaffold-GS · Mip-NeRF360 | SSIM: 0.825 -> 0.837 | No clear effect |
| replace Scaffold-GS growing with full HGS | Scaffold-GS · Tanks&Temples | LPIPS: 0.170 -> 0.126 | Improved |
| replace Scaffold-GS growing with full HGS | Scaffold-GS · Deep Blending | LPIPS: 0.245 -> 0.225 | Improved |
| use HGS instead of Scaffold-GS growing (efficiency cost) | Scaffold-GS · Tanks&Temples | training time and FPS: 20.4m -> 66.2m; 125 -> 42 FPS | Hurt |
| use Effi-HGS instead of full HGS | HGS · Tanks&Temples | training time and FPS: 66.2m -> 28.6m; 42 -> 87 FPS | Improved |
| lower k in PGHGS (3 -> 2) (ablation) | HGS · Tanks&Temples | PSNR vs LPIPS: PSNR 26.36 -> 26.34; LPIPS 0.126 -> 0.123 | Mixed |
| increase k in PGHGS (3 -> 4) (ablation) | HGS · Tanks&Temples | PSNR, LPIPS: 26.36 -> 26.26; 0.126 -> 0.131 | Hurt |
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.
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · better on 6 of 8 shared results
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 3 of 3 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
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.93)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.93)
- 3D-HGS: 3D Half-Gaussian Splatting (CVPR 2025 · similarity 0.93)
- LP-3DGS: Learning to Prune 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · 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.
