Research map / Point clouds / Registration and matching
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
Jiaolong Yang, Hongdong Li, Dylan Campbell, Yunde Jia
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 |
|---|---|---|---|
| use a distance transform instead of a kd-tree for closest-point distances (ablation) | Go-ICP · bunny and dragon registration | running time: 40-50 times faster | Improved |
| integrate local ICP into the BnB search (ablation) | Go-ICP · bunny registration | registration convergence | Improved |
| add trimming for partial overlap | Go-ICP · partially overlapping point-sets | running time | Hurt |
| increase number of data points (ablation) | Go-ICP · bunny and dragon | running time | Hurt |
| add Gaussian noise to model and data point-sets (up to sigma 0.02) (ablation) | Go-ICP · bunny | running time | Improved |
| use a smaller convergence threshold (ablation) | Go-ICP · bunny and dragon | running time | Hurt |
| raise optimal registration error (RMS above 0.03) (ablation) | Go-ICP · bunny | running time | Hurt |
| vary trimming percentage 5%, 10%, 20% (ablation) | Go-ICP with trimming · bunny | registration success | No clear effect |
| use a 300x300x300 DT rather than kd-tree (ablation) | Go-ICP · optimality tests on synthetic and real data | registration result | No clear effect |
Closest papers by meaning
- Fast and Robust Iterative Closest Point (TPAMI 2021 · similarity 0.92)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (AAAI 2025 · similarity 0.87)
- Efficient and Robust Registration on the 3D Special Euclidean Group (ICCV 2019 · similarity 0.87)
- An Approach to Robust ICP Initialization (TPAMI 2023 · similarity 0.86)
- Global Optimality for Point Set Registration Using Semidefinite Programming (CVPR 2020 · similarity 0.86)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.85)
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.
