Research map / 3D vision / Gaussian splatting
CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
Zhigang Cheng, Mingchao Sun, Yu Liu, Zengye Ge, Luyang Tang, Mu Xu, Yangyan Li, Peng Pan
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 weight w_s to training loss (ablation) | CLoD-GS · BungeeNeRF | PSNR: 27.39 -> 27.59 | Improved |
| add primitive count regularization loss (ablation) | CLoD-GS · BungeeNeRF | PSNR: 27.56 -> 27.59 | No clear effect |
| add both weight and regularization loss (ablation) | CLoD-GS · BungeeNeRF | PSNR: 26.71 -> 27.59 | Improved |
| add both weight and regularization loss (ablation) | CLoD-GS · Deep Blending | PSNR: 29.57 -> 29.76 | Improved |
| increase maximum virtual scale from 1 to 7 (ablation) | CLoD-GS · BungeeNeRF | #Gaussians (k): 4185 -> 1855 | Improved |
| CLoD-GS vs 3DGS at scale=1 | 3DGS · BungeeNeRF | #Gaussians (k): 6733 -> 4185 | Improved |
| apply CLoD-GS on MipNeRF360 with universal parameters | 3DGS · MipNeRF360 | PSNR: 27.59 -> 27.01 | Hurt |
| increase maximum virtual scale from 1 to 7 (ablation) | CLoD-GS · Deep Blending | FPS: 128.68 -> 187.48 | 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 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
- LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering (NeurIPS 2025 · similarity 0.92)
- LOD-GS: Achieving Levels of Detail using Scalable Gaussian Soup (CVPR 2025 · similarity 0.91)
- MACRO: Training-free Multi-plane Attention for Closeup Render Optimization (NeurIPS 2026 · similarity 0.89)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.89)
- Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting (AAAI 2025 · 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.
