Research map / 3D vision / Gaussian splatting
Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis
Chen Zhao, Xuan Wang, Tong Zhang, Saqib Javed, Mathieu Salzmann
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 |
|---|---|---|---|
| use uncertainty-aware perturbation instead of random perturbation of all Gaussians (ablation) | SE-GS · LLFF 3-view, 2000 iterations | PSNR: 18.63 -> 20.34 | Improved |
| use uncertainty-aware perturbation instead of gradient-aware perturbation (ablation) | SE-GS · LLFF 3-view, 2000 iterations | PSNR: 19.18 -> 20.34 | Improved |
| add self-ensembling to 3DGS (3 views) | 3DGS · LLFF 3-view | PSNR: 19.22 -> 20.79 | Improved |
| add self-ensembling to 3DGS (3 views) | 3DGS · DTU 3-view | PSNR: 17.67 -> 19.24 | Improved |
| add self-ensembling to 3DGS (10 views) | 3DGS · MVImgNet 10-view | PSNR: 31.82 -> 32.68 | Improved |
| train more 3DGS models in CoR-GS (2 to 8) (ablation) | CoR-GS · LLFF 3-view | PSNR: peak at 6 models | Mixed |
| perturb the Delta-model every 100 iterations instead of 500 (ablation) | SE-GS · LLFF 3-view | PSNR | Hurt |
| perturb every 900 iterations instead of 500 (ablation) | SE-GS · LLFF 3-view | PSNR | Hurt |
| use strong noise level omega 0.3 or 0.2 instead of decayed 0.08 to 0.02 (ablation) | SE-GS · LLFF 3-view | PSNR | Hurt |
| use small fixed omega 0.01 instead of decayed omega (ablation) | SE-GS · LLFF 3-view | PSNR | Hurt |
| use FSGS depth supervision instead of vanilla 3DGS (9 views) | FSGS · LLFF 9-view | PSNR: 25.44 -> 25.31 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · better on 11 of 11 shared results
- FreeNeRF — FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization (CVPR 2023) · better on 1 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
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.92)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.91)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus (NeurIPS 2024 · similarity 0.91)
- DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · 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.
