Research map / Point clouds / Registration and matching
GraphCPD: Coherent Point Drift for Point Cloud Registration via Graph Signal Processing
Yingcheng Lai, Xingjian Wang, Li Chai
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 |
|---|---|---|---|
| replace isotropic covariance with local graph Laplacian density model (ablation) | GraphCPD · Dragon | AngErr (deg): 0.1542 -> 0.091 | Improved |
| replace isotropic covariance with local graph Laplacian density model (ablation) | GraphCPD · Armadillo | AngErr (deg): 0.3836 -> 0.095 | Improved |
| use weighted global graph instead of unweighted for high-pass filtering (ablation) | GraphCPD · Dragon | AngErr (deg): 0.232 -> 0.091 | Improved |
| use weighted global graph instead of unweighted for high-pass filtering (ablation) | GraphCPD · Armadillo | AngErr (deg): 0.308 -> 0.095 | Improved |
| increase kmatch from 50 to 250 (ablation) | GraphCPD · Dragon | AngErr (deg): 0.242 -> 0.073 | Improved |
| increase kmatch from 50 to 250 (ablation) | GraphCPD · Dragon | runtime (s): 2.559 -> 10.045 | Hurt |
| increase kmatch from 50 to 250 (ablation) | GraphCPD · Armadillo | AngErr (deg): 0.215 -> 0.071 | Improved |
| increase kmatch from 50 to 250 (ablation) | GraphCPD · Armadillo | runtime (s): 2.354 -> 11.592 | Hurt |
| increase local graph size k from 10 to 20 (ablation) | GraphCPD · Dragon | AngErr (deg): 0.091 -> 0.362 | Hurt |
| decrease local graph size k from 10 to 5 (ablation) | GraphCPD · Dragon | AngErr (deg): 0.091 -> 0.103 | Hurt |
| increase local graph size k from 10 to 20 (ablation) | GraphCPD · Armadillo | AngErr (deg): 0.095 -> 0.244 | Hurt |
| increase local graph size k from 10 to 20 (ablation) | GraphCPD · Dragon | runtime (s): 2.950 -> 2.683 | Improved |
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.
- LSG-CPD — LSG-CPD: Coherent Point Drift With Local Surface Geometry for Point Cloud Registration (ICCV 2021) · better on 2 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
- LSG-CPD: Coherent Point Drift With Local Surface Geometry for Point Cloud Registration (ICCV 2021 · similarity 0.91)
- SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondences (CVPR 2019 · similarity 0.89)
- FastMAC: Stochastic Spectral Sampling of Correspondence Graph (CVPR 2024 · similarity 0.89)
- GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning (CVPR 2025 · similarity 0.87)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (AAAI 2025 · similarity 0.87)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.86)
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.
