Research map / Point clouds / Registration and matching
3D Registration of Curves and Surfaces Using Local Differential Information
Carolina Raposo, João P. Barreto
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 local point-plus-tangent/normal 2-tuples for global registration instead of Super4PCS | Curve vs surface registration · Synthetic data, across input sizes and noise conditions | registration accuracy | Improved |
| Use local point-plus-tangent/normal 2-tuples for global registration instead of Super4PCS | Curve vs surface registration · Synthetic data | computational time | Improved |
| Use the proposed curve-surface registration method rather than FGR | Curve vs surface registration · Synthetic data | registration success | Improved |
| Increase curve input from smaller subsets to the full curve | Proposed curve vs surface method · Synthetic data | registration accuracy | Improved |
| Use the proposed curve-curve method rather than Super4PCS | Curve vs curve registration · Synthetic data, noise-free | registration accuracy | Improved |
| Use the proposed curve-curve method rather than Super4PCS | Curve vs curve registration · Synthetic data with noise, very small input | registration accuracy | Improved |
| Add noise to the curve data | Proposed curve-curve method · Synthetic curve vs curve | registration accuracy | Hurt |
| Use the proposed curve-curve method rather than FGR | Curve vs curve registration · Synthetic data with noise | registration success | Improved |
| Add 20%-40% outliers to acquired curves | Proposed curve vs surface method · Dry knee CAOS experiment | registration accuracy | No clear effect |
Closest papers by meaning
- A General Framework for Curve and Surface Comparison and Registration With Oriented Varifolds (CVPR 2017 · similarity 0.86)
- Higher-Order Graph Principles towards Non-Rigid Surface Registration (TPAMI 2016 · similarity 0.85)
- Surface Registration via Foliation (ICCV 2017 · similarity 0.85)
- Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration (CVPR 2022 · similarity 0.85)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.84)
- SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency (CVPR 2024 · similarity 0.83)
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.
