Research map / Point clouds / Point cloud classification
The Perfect Match: 3D Point Cloud Matching With Smoothed Densities
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 SDV voxelization instead of a binary occupancy grid (ablation) | 3DSmoothNet · 3DMatch | average recall: 92.5 -> 94.7 | Helped |
| Use SDV voxelization instead of a binary occupancy grid (ablation) | 3DSmoothNet · 3DRotatedMatch, τ2 = 0.2 | average recall: 63.6 -> 72.8 | Helped |
| Add LRF alignment (ablation) | 3DSmoothNet · 3DMatch | average recall: 96.3 -> 94.7 | Hurt |
| Add LRF alignment (ablation) | 3DSmoothNet · 3DRotatedMatch | average recall: 11.6 -> 94.9 | Helped |
| Increase descriptor dimension from 16 to 32 | 3DSmoothNet · 3DMatch | average recall: 92.8 -> 94.7 | Helped |
| Increase descriptor dimension from 16 to 32 | 3DSmoothNet · ETH | average recall: 48.2 -> 79.0 | Helped |
| Train on indoor RGB-D scenes and evaluate on outdoor laser scans | 3DSmoothNet (32 dim) · ETH | average recall: 79.0 | Helped |
| Rotate all point-cloud fragments | 3DSmoothNet (32 dim) · 3DMatch to 3DRotatedMatch | average recall: 94.7 -> 94.9 | No clear effect |
| Reduce point density to 12.5% in both fragments | 3DSmoothNet (32 dim) · 3DSparseMatch, Both | average recall: 95.0 -> 93.7 | Hurt |
Closest papers by meaning
- Dataset Distillation of 3D Point Clouds via Distribution Matching (NeurIPS 2025 · similarity 0.89)
- DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features (CVPR 2025 · similarity 0.88)
- APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction (NeurIPS 2025 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.87)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · similarity 0.87)
- DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching (CVPR 2024 · similarity 0.87)
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.