Research map / Point clouds / Registration and matching
Gravitational Approach for Point Set Registration
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Gravitational Approach instead of ICP | Rigid point set registration · Synthetic Stanford Bunny with noise | mean distance and RMSE | Helped |
| Use Gravitational Approach instead of CPD | Rigid point set registration · Synthetic Stanford Bunny with 50% uniformly distributed noise | mean distance | Helped |
| Use Gravitational Approach instead of CPD | Rigid point set registration · Orion constellation images with about 95% template noise | registration success | Helped |
| Set different particle masses using grayscale intensity | Gravitational Approach · Orion constellation images with about 95% template noise | registration success | Helped |
| Set the gravitational parameter or CPD noise parameter suboptimally | GA and CPD · Human scan with clustered spherical outliers | registration accuracy | Mixed |
| Increase the viscosity parameter η (ablation) | Gravitational Approach · Point set registration | convergence speed | Mixed |
| Tune gravitational strength G and viscosity η jointly (ablation) | Gravitational Approach · Point set registration | registration performance | Mixed |
| Use a suboptimal scale-resolving parameter setting (ablation) | Gravitational Approach · Rigid point set registration with scale | registration stability | Hurt |
Closest papers by meaning
- Global Optimality for Point Set Registration Using Semidefinite Programming (CVPR 2020 · similarity 0.82)
- Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration (CVPR 2022 · similarity 0.81)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.81)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (AAAI 2025 · similarity 0.80)
- Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents (ICML 2025 · similarity 0.79)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.78)
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.