Research map / Point clouds / Registration and matching
PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
Yu Zhang, Junle Yu, Xiaolin Huang, Wenhui Zhou, Ji Hou
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 PCR-CG color feature projection | Predator · 3DLoMatch (5000 points) | Registration Recall %: 59.8 -> 66.3 | Improved |
| add PCR-CG | Predator · 3DLoMatch (500 points) | Registration Recall %: 60.8 -> 68.5 | Improved |
| add PCR-CG | Predator · 3DMatch (1000 points) | Registration Recall %: 90.6 -> 90.0 | No clear effect |
| add PCR-CG | CoFiNet · 3DLoMatch (5000 points) | Registration Recall %: 64.4 -> 67.9 | Improved |
| add PCR-CG | GeoTransformer · 3DLoMatch | Registration Recall %: 74.0 -> 76.4 | Improved |
| add PCR-CG | GeoTransformer · 3DMatch | Registration Recall %: 91.5 -> 92.5 | Improved |
| use explicit instead of implicit projection (Pri3D features) (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 63.4 -> 66.3 | Improved |
| use explicit instead of implicit projection (RGB values) (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 60.5 -> 60.4 | No clear effect |
| lift deep Pri3D features instead of RGB values (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 60.4 -> 66.3 | Improved |
| lift deep Pri3D features instead of SIFT features (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 64.8 -> 66.3 | Improved |
| use window size 11x11 instead of 3x3 (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 63.1 -> 66.3 | Improved |
| use 2 views instead of 1 (ablation) | PCR-CG · 3DLoMatch RR 5000 | Registration Recall %: 62.0 -> 63.4 | Improved |
Later papers that compared with this method
1 later accepted paper reports PCR-CG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- SemReg: Semantics Constrained Point Cloud Registration (ECCV 2024 · better on 2 of 2 shared results)
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.
- SpinNet — SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration (CVPR 2021) · better on 2 of 2 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
- ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion (CVPR 2024 · similarity 0.91)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.88)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- Generative Point Cloud Registration (ICML 2025 · similarity 0.88)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.87)
- Partial Point Cloud Registration with Multi-view 2D Image Learning (AAAI 2025 · similarity 0.87)
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.
