Research map / 3D vision / Gaussian splatting
A Step to Decouple Optimization in 3DGS
Renjie Ding, Yaonan Wang, Min Liu, Jialin Zhu, Jiazheng Wang, Jiahao Zhao, Wenting Shen, Feixiang He, Xiang Chen
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 AdamW-GS | 3DGS-MCMC · Mip-NeRF360 | PSNR: 27.948 -> 28.219 | Improved |
| add AdamW-GS | 3DGS-MCMC · Mip-NeRF360 | training time (min): 46.81 -> 39.77 | Improved |
| add AdamW-GS | vanilla 3DGS · Mip-NeRF360 | PSNR: 27.506 -> 27.678 | Improved |
| add AdamW-GS | vanilla 3DGS · Mip-NeRF360 | LPIPS: 0.216 -> 0.220 | Hurt |
| add AdamW-GS | vanilla 3DGS · Mip-NeRF360 | active primitives: -49.3% | Improved |
| replace Adam with Sparse Adam in the optimization stage (ablation) | 3DGS · Mip-NeRF360 | PSNR: 27.507 -> 27.285 | Hurt |
| add Re-State Regularization with Decoupled Attribute Regularization (ablation) | 3DGS-MCMC + Sparse Adam · Mip-NeRF360 | PSNR: 28.075 -> 28.185 | Improved |
| raise RSR sampling ratio with coupled L1 regularization (ablation) | 3DGS-MCMC · Mip-NeRF360 indoor Room | PSNR: 32.514 -> 31.179 | Hurt |
| raise RSR sampling ratio with DAR (ablation) | 3DGS-MCMC · Mip-NeRF360 indoor | PSNR: Kitchen 32.546 -> 32.298 | No clear effect |
| add AIU to Sparse Adam (ablation) | 3DGS-MCMC · Mip-NeRF360 | PSNR: 27.998 -> 28.050 | Mixed |
| remove opacity reset (ablation) | 3DGS + AdamW-GS · Mip-NeRF360 | active primitives: -49.3% -> -46.9% | Hurt |
| add AdamW-GS | MaskGaussian · Mip-NeRF360 indoor | PSNR: 30.988 -> 31.199 | Improved |
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.
- MaskGaussian — MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks (CVPR 2025) · better on 4 of 5 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
- 3D Student Splatting and Scooping (CVPR 2025 · similarity 0.90)
- LP-3DGS: Learning to Prune 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025 · similarity 0.89)
- ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model (NeurIPS 2024 · similarity 0.89)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.89)
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.
