Research map / Point clouds / Registration and matching
A Probabilistic Framework for Color-Based 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 component-specific color distributions, conditionally dependent on spatial mixture components | JRMPS point-set registration · Stanford Lounge pairwise | Failure rate (%): 3.41 -> 0.74 | Helped |
| Use component-specific color distributions, conditionally dependent on spatial mixture components | JRMPS point-set registration · Stanford Lounge joint multi-view | Failure rate (%): 0.467 -> 0.067 | Helped |
| Replace the proposed spatially conditioned color model with direct joint point-color mixture components (ablation) | Color-based registration · Stanford Lounge pairwise | Failure rate (%): 0.74 -> 2.14 | Hurt |
| Replace the proposed spatially conditioned color model with independent spatial and color distributions (ablation) | Color-based registration · Stanford Lounge pairwise | Failure rate (%): 0.74 -> 3.41 | Hurt |
| Increase the number of feature components per HSV dimension (ablation) | Color-based registration · Stanford Lounge pairwise | Average inlier rotation error | Helped |
| Increase the number of feature components per HSV dimension (ablation) | Direct Approach · Stanford Lounge pairwise | Average inlier rotation error | Hurt |
| Add color information to JRMPS | JRMPS · Stanford Lounge pairwise | Avg. error: 1.68 ·10−2 -> 1.47 ·10−2 | Helped |
| Add color information to JRMPS | JRMPS · Stanford Lounge joint multi-view | Avg. error: 0.913 ·10−2 -> 0.768 ·10−2 | Helped |
Closest papers by meaning
- ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion (CVPR 2024 · similarity 0.88)
- Pre-training LiDAR-based 3D Object Detectors through Colorization (ICLR 2024 · similarity 0.85)
- Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model (CVPR 2025 · similarity 0.84)
- GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning (CVPR 2025 · similarity 0.84)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.84)
- A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration (NeurIPS 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.