Research map / 3D vision / Gaussian splatting
Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration
Jaewon Lee, Mangyu Kong, Euntai Kim
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 CLIP histogram to node matching (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RRE: 4.865 -> 3.247 | Improved |
| add TRIMs geometric node selection (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RRE: 6.047 -> 3.247 | Improved |
| add TRIMs geometric node selection (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RTE: 0.140 -> 0.039 | Improved |
| add maximum clique search after TRIMs (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RRE: 6.575 -> 3.247 | Improved |
| add FPFH features (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RRE: 3.247 -> 3.190 | Improved |
| add FPFH features (ablation) | Graph-GSReg coarse · ScanNet-GSReg | time (s): 2.784 -> 3.645 | Hurt |
| use maximum clique instead of best-CLIP-score maximal clique (ablation) | Graph-GSReg coarse · ScanNet-GSReg | RRE: 3.981 -> 3.247 | Improved |
| use CLIP histogram-5 instead of default (ablation) | Graph-GSReg coarse · ScanNet-GSReg | time (s): 2.784 -> 4.341 | Hurt |
| add ICP fine refinement | Graph-GSReg · ScanNet-GSReg | RRE: 3.247 -> 1.970 | Improved |
| add ICP fine refinement | Graph-GSReg · uHumans2 | RRE: 1.748 -> 0.711 | Improved |
| add voxelization before merging (ablation) | Graph-GSReg merging · ScanNet-GSReg | size (MB): 238.10 -> 82.84 | Improved |
| add voxelization before merging (ablation) | Graph-GSReg merging · ScanNet-GSReg | PSNR: 21.4538 -> 21.5248 | No clear effect |
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.
- GaussReg — GaussReg: Fast 3D Registration with Gaussian Splatting (ECCV 2024) · 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
- Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting (ICLR 2025 · similarity 0.92)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene (AAAI 2025 · similarity 0.90)
- DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus (NeurIPS 2024 · similarity 0.90)
- Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images (NeurIPS 2024 · similarity 0.90)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 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.
