Research map / 3D vision / Gaussian splatting
Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation
Ziyang Huang, Jiagang Chen, Jin Liu, Shunping Ji
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 Adaptive Weighted SGLD (ablation) | 3DGSMCMC · Tanks & Temples Train | PSNR: 22.47 -> 22.74 | Improved |
| add Adaptive Weighted SGLD (ablation) | 3DGSMCMC · Tanks & Temples Train | LPIPS: 0.240 -> 0.180 | Improved |
| add Adaptive Weighted SGLD (ablation) | 3DGSMCMC · Tanks & Temples Truck | PSNR: 26.11 -> 26.49 | Improved |
| add Adaptive Weighted SGLD (ablation) | 3DGSMCMC · Tanks & Temples Truck | LPIPS: 0.140 -> 0.104 | Improved |
| add LQNAdam on top of AW-SGLD (ablation) | Opt3DGS · Tanks & Temples Train | PSNR: 22.74 -> 23.01 | Improved |
| add LQNAdam on top of AW-SGLD (ablation) | Opt3DGS · Tanks & Temples Truck | PSNR: 26.49 -> 26.61 | Improved |
| add both components, training time cost (ablation) | Opt3DGS · Tanks & Temples Train | time (minutes): 11 -> 12 | No clear effect |
| replace 3DGSMCMC optimization with Opt3DGS | 3DGSMCMC · Tanks & Temples (SfM init) | LPIPS: 0.190 -> 0.139 | Improved |
| replace 3DGSMCMC optimization with Opt3DGS | 3DGSMCMC · MipNeRF360 (SfM init) | SSIM: 0.900 -> 0.897 | Hurt |
| replace 3DGSMCMC optimization with Opt3DGS under random initialization | 3DGSMCMC · DeepBlending (random init) | LPIPS: 0.320 -> 0.236 | Improved |
| replace 3DGSMCMC optimization with Opt3DGS under random initialization | 3DGSMCMC · MipNeRF360 (random init) | LPIPS: 0.190 -> 0.149 | Improved |
| set flattening coefficient zeta near 0.8 (ablation) | Opt3DGS · Tanks & Temples | PSNR | Improved |
Closest papers by meaning
- AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.92)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- 3D Student Splatting and Scooping (CVPR 2025 · similarity 0.91)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.91)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.90)
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.
