Research map / 3D vision / Gaussian splatting
GaussReg: Fast 3D Registration with Gaussian Splatting
Jiahao Chang, Yinglin Xu, Yihao Li, Yuantao Chen, Wensen Feng, Xiaoguang Han
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 image-guided fine registration after coarse registration (ablation) | GaussReg · ScanNet-GSReg | RTE: 0.061 -> 0.042 | Improved |
| add image-guided fine registration on real-world scenes (ablation) | GaussReg · GSReg | RRE: 6.904 -> 2.989 | Improved |
| use HLoc instead of learned fine registration after coarse alignment (ablation) | GaussReg · ScanNet-GSReg | success ratio: 1.000 -> 0.512 | Hurt |
| GS registration vs HLoc image matching (SfM) baseline | GaussReg · ScanNet-GSReg | time (s): 212.3 -> 4.8 | Improved |
| use point cloud registration baselines on noisy GS point clouds | FGR, REGTR · ScanNet-GSReg | RRE: 157.126 (FGR), 80.095 (REGTR) vs 2.827 | Hurt |
| increase top-k camera pairs from 5 to 10 (ablation) | overlap image selection · ScanNet-GSReg | RTE: 0.115 -> 0.042 | Improved |
| increase top-k beyond 10 (ablation) | overlap image selection · ScanNet-GSReg | RTE: 0.042 -> 0.063 (k=20) | No clear effect |
| add image-guided 3D (I3D) feature extraction instead of MVSNet depth projection (ablation) | GaussReg fine registration · ScanNet-GSReg | RSE: RRE 3.169 -> 2.827, RSE 0.061 -> 0.032, RTE 0.036 -> 0.042, RDE 0.066 -> 0.080 | Mixed |
| apply coarse registration alone to object-level registration | GaussReg coarse · Objaverse | RRE: 9.67 -> 2.47 | Improved |
Later papers that compared with this method
2 later accepted papers report GaussReg as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment (CVPR 2026 · better on 9 of 9 shared results)
- Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration (ECCV 2026 · 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
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting (CVPR 2025 · similarity 0.89)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.89)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction (CVPR 2025 · similarity 0.89)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 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.
