Research map / 3D vision / Gaussian splatting
Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting
Qinzheng Zhou, Zaychik Liu, Lijing Lu, Zhihang Li
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 confidence-guided hierarchical aggregation (ablation) | 3DGS (CAGS) · ablation, original Res | PSNR: 15.32 -> 18.45 | Improved |
| add multi-scale pseudo-view regularization (ablation) | 3DGS (CAGS) · ablation, original Res | PSNR: 15.32 -> 16.43 | Improved |
| add multi-scale regularization on top of hierarchical aggregation (ablation) | CAGS · ablation, original Res | PSNR: 18.45 -> 18.83 | Improved |
| add multi-scale regularization on top of hierarchical aggregation (ablation) | CAGS · ablation, 1/2 Res | PSNR: 19.10 -> 19.50 | Improved |
| add hierarchical aggregation on top of multi-scale regularization (ablation) | CAGS · ablation, original Res | PSNR: 16.43 -> 18.83 | Improved |
| plug CAGS into DropGaussian | DropGaussian · DTU original Res | PSNR: 17.45 -> 19.13 | Improved |
| plug CAGS into FSGS | FSGS · DTU original Res | PSNR: 17.32 -> 18.67 | Improved |
| plug CAGS into CoR-GS | CoR-GS · DTU original Res | PSNR: 17.51 -> 19.25 | Improved |
| use CAGS instead of NexusGS at original resolution | sparse-view 3DGS · LLFF original Res | PSNR: 16.12 -> 18.85 | Improved |
| use CAGS instead of NexusGS at 1/4 resolution | sparse-view 3DGS · LLFF 1/4 Res | PSNR: 20.29 -> 20.62 | Improved |
| lower input resolution (full to 1/8) in plain 3DGS | 3DGS · empirical study (qualitative) | visual quality | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- NexusGS — NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting (CVPR 2025) · better on 7 of 7 shared results
- DropGaussian — DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025) · better on 4 of 4 shared results
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · 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
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.92)
- S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting (CVPR 2025 · similarity 0.92)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.92)
- DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025 · similarity 0.91)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.91)
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.
