Research map / Point clouds / Registration and matching
3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder
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 |
|---|---|---|---|
| Replace key-points with RSCS super-points (ablation) | FPFH registration · Challenging Dataset Registration | RRE (degrees): 12.2±4.8 -> 9.1±2.6 | Helped |
| Replace key-points with RSCS super-points (ablation) | FPFH registration · Challenging Dataset Registration | Binary success rate: 8/12 (67%) -> 8/12 (67%) | No clear effect |
| Replace FPFH with PCA features (ablation) | RSCS registration · Challenging Dataset Registration | RRE (degrees): 9.1±2.6 -> 7.2±2.3 | Helped |
| Replace PCA features with auto-encoder features (ablation) | RSCS registration · Challenging Dataset Registration | RRE (degrees): 7.2±2.3 -> 2.5±1.2 | Helped |
| Replace PCA features with auto-encoder features (ablation) | RSCS registration · Challenging Dataset Registration | Binary success rate: 8/12 (67%) -> 10/12 (83%) | Helped |
| Increase random point relocation noise | LORAX · Controlled noise sensitivity tests | Binary success rate | No clear effect |
| Increase point removal or density change | LORAX · Controlled density sensitivity tests | Binary success rate | No clear effect |
| Increase occlusion by removing points within local spheres | LORAX · Controlled occlusion sensitivity tests | Binary success rate | Hurt |
Closest papers by meaning
- Robust Point Cloud Registration Framework Based on Deep Graph Matching (CVPR 2021 · similarity 0.90)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · similarity 0.88)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.88)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · similarity 0.88)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension (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.