Research map / Point clouds / Registration and matching
Density Adaptive Point Set Registration
Read the paperCheck 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 |
|---|---|---|---|
| Add empirical observation-density weights to JRMPC | JRMPC · Synthetic pairwise | failure rate (%): 85 % -> 2 % | Helped |
| Add empirical observation-density weights to JRMPC | JRMPC · VPS + TLS ETH pairwise | failure rate (%): 90.4 -> 43.3 | Helped |
| Add empirical observation-density weights to JRMPC | JRMPC · VPS + TLS ETH pairwise | average inlier angular error (°): 2.44$\pm$0.87 -> 1.45$\pm$0.89 | Helped |
| Add empirical density adaptation and color features | CPPSR · VPS indoor multi-view | failure rate (%): 87.4 -> 14.5 | Helped |
| Add empirical density adaptation and color features | CPPSR · VPS indoor multi-view | average inlier angular error (°): 2.57$\pm$0.837 -> 1.26$\pm$0.61 | Helped |
| Use empirically optimized re-sampling with JRMPC | JRMPC · VPS + TLS ETH pairwise | failure rate (%): 90.4 -> 46.0 | Helped |
| Change clipping threshold T from 8 to 6 (ablation) | DARE · VPS + TLS ETH parameter analysis | failure rate (%): 42.3 -> 43.8 | Hurt |
| Change clipping threshold T from 8 to 10 (ablation) | DARE · VPS + TLS ETH parameter analysis | failure rate (%): 42.3 -> 41.3 | Helped |
| Change clipping threshold T from 8 to 12 (ablation) | DARE · VPS + TLS ETH parameter analysis | average inlier error: 1.49 -> 1.59 | Hurt |
| Change neighbor count L from 10 to 5 (ablation) | DARE · VPS + TLS ETH parameter analysis | average inlier error: 1.49 -> 1.53 | Hurt |
| Change neighbor count L from 10 to 5 (ablation) | DARE · VPS + TLS ETH parameter analysis | failure rate (%): 42.3 -> 42.0 | Helped |
| Increase neighbor count L (ablation) | DARE · VPS + TLS ETH parameter analysis | average inlier error: 1.49 -> 1.46 (L=20); 1.45 (L=40) | Helped |
Closest papers by meaning
- A Probabilistic Framework for Color-Based Point Set Registration (CVPR 2016 · similarity 0.88)
- C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion (CVPR 2026 · similarity 0.88)
- Point Density-Aware Voxels for LiDAR 3D Object Detection (CVPR 2022 · similarity 0.87)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.86)
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.85)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 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.