Research map / 3D vision / Gaussian splatting
Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D 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 to 3DGS (ablation) | 3DGS · Mip-NeRF360 (ablation) | LPIPS: 0.216 -> 0.195 | Improved |
| add depth reinitialization after blur split (ablation) | 3DGS + Blur Split · Mip-NeRF360 (ablation) | LPIPS: 0.195 -> 0.175 | Improved |
| add blur split to 3DGS (ablation) | 3DGS · Mip-NeRF360 (ablation) | PSNR: 27.47 -> 27.47 | No clear effect |
| reinitialize with blending depth instead of midpoint depth (ablation) | depth reinitialization · Mip-NeRF360 (ablation) | PSNR: 27.54 -> 17.67 | Hurt |
| use Gaussian center instead of midpoint depth (ablation) | depth reinitialization · Mip-NeRF360 (ablation) | PSNR: 27.54 -> 27.57 | No clear effect |
| add aggressive model growth to Mini-Splatting* (ablation) | Mini-Splatting* · Mip-NeRF360 (ablation) | training time: 7min59s -> 4min4s | Improved |
| add occluded Gaussian culling after aggressive growth (ablation) | MSv2 · Mip-NeRF360 (ablation) | training time: 4min4s -> 3min34s | Improved |
| add aggressive model growth to Mini-Splatting* (ablation) | Mini-Splatting* · Mip-NeRF360 (ablation) | PSNR: 27.23 -> 27.43 | Improved |
| add occluded Gaussian culling (ablation) | MSv2 · Mip-NeRF360 (ablation) | PSNR: 27.43 -> 27.33 | Hurt |
| use 3K-iteration shortened densification instead of full aggressive growth (ablation) | MSv2 · Mip-NeRF360 (ablation) | PSNR: 27.33 -> 26.49 | Hurt |
| use lower gradient threshold instead of full aggressive growth (ablation) | MSv2 · Mip-NeRF360 (ablation) | PSNR: 27.33 -> 26.58 | Hurt |
| use only Agg-Depth instead of full aggressive growth (ablation) | MSv2 · Mip-NeRF360 (ablation) | PSNR: 27.33 -> 27.12 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 0 of 1 shared result
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)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.93)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.93)
- Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis (NeurIPS 2024 · similarity 0.92)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.92)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (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.
