Research map / 3D vision / Gaussian splatting
Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting
Junseo Koo, Jinseo Jeong, Gunhee Kim
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 |
|---|---|---|---|
| replace scalar alpha blending with Gaussian Blending | Analytic-Splatting / Mip-Splatting · Multi-scale Blender (train x1) | PSNR avg: 31.59 -> 35.58 | Improved |
| replace scalar alpha blending with Gaussian Blending | Mip-Splatting · Multi-scale Blender (train x1/8) | PSNR avg: 29.64 -> 31.04 | Improved |
| replace scalar alpha blending with Gaussian Blending | Mip-Splatting · Multi-scale Blender (multi-scale training) | PSNR avg: 34.72 -> 36.19 | Improved |
| replace scalar alpha blending with Gaussian Blending | Mip-Splatting · Mip-NeRF 360 (train x1) | PSNR avg: 28.47 -> 29.17 | Improved |
| replace scalar alpha blending with Gaussian Blending | Mip-Splatting · Mip-NeRF 360 (multi-scale training) | PSNR avg: 29.25 -> 29.53 | Improved |
| swap in Gaussian Blending kernel at test time only (ablation) | Mip-Splatting · Multi-scale Blender (train x1) | PSNR avg: 31.73 -> 35.54 | Improved |
| swap in Gaussian Blending kernel at test time only (ablation) | Mip-Splatting · Multi-scale Blender (train x1/8) | PSNR avg: 29.64 -> 29.12 | Hurt |
| swap in Gaussian Blending kernel at test time only (ablation) | Analytic-Splatting · Multi-scale Blender (train x1/8) | PSNR avg: 29.53 -> 28.78 | Hurt |
| use Gaussian Blending kernel in training and inference (ablation) | Scaffold-GS · Multi-scale Blender (train x1) | PSNR avg: 24.92 -> 32.47 | Improved |
| reimplement spatial alpha blending in native kernel (ablation) | 2DGS · Multi-scale Blender (train x1) | PSNR avg: 23.79 -> 33.79 | Improved |
| use Gaussian Blending kernel in training and inference (ablation) | Scaffold-GS · Multi-scale Blender (train x1/8) | PSNR avg: 22.37 -> 30.41 | Improved |
| use Gaussian Blending kernel at x1 resolution | Gaussian Blending vs Mip-Splatting · Multi-scale Blender (train x1) | PSNR x1: 33.54 -> 33.92 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 7 of 7 shared results
- Analytic-Splatting — Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration (ECCV 2024) · better on 6 of 6 shared results
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · better on 2 of 2 shared results
- Tri-MipRF — Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing 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
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.93)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- Sort-free Gaussian Splatting via Weighted Sum Rendering (ICLR 2025 · similarity 0.92)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.92)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 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.
