Research map / Point clouds / Registration and matching
Reliable Inlier Evaluation for Unsupervised Point Cloud 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 |
|---|---|---|---|
| Use RIENet instead of RPM-Net | Point cloud registration · ModelNet40 Same | MAE(R): 0.0051 -> 0.0033 | Helped |
| Use RIENet instead of RPM-Net | Point cloud registration · ModelNet40 Unseen | MAE(R): 0.0064 -> 0.0059 | Helped |
| Use RIENet instead of RPM-Net | Point cloud registration · ModelNet40 Noise | MAE(R): 0.0075 -> 0.0069 | Helped |
| Use RIENet instead of CEMNet | Point cloud registration · ICL-NUIM | MAE(R): 0.2374 -> 0.0492 | Helped |
| Use RIENet instead of CEMNet | Point cloud registration · 7Scenes | MAE(R): 0.0559 -> 0.0121 | Helped |
| Use RIENet instead of RPM-Net | Point cloud registration · KITTI | MAE(R): 0.9164 -> 0.8251 | Helped |
| Add inlier evaluation to the baseline (ablation) | RIENet on ModelNet40 · ModelNet40 | MAE(R): 2.2207 -> 0.1638 | Helped |
| Add matching map refinement to BS + IE (ablation) | RIENet on ModelNet40 · ModelNet40 | MAE(R): 0.1638 -> 0.0266 | Helped |
| Add spatial consistency loss to global alignment loss (ablation) | RIENet on 7Scenes · 7Scenes | MAE(R): 0.6303 -> 0.1165 | Helped |
| Add neighborhood consensus loss to GAL + SCL (ablation) | RIENet on 7Scenes · 7Scenes | MAE(R): 0.1165 -> 0.0121 | Helped |
| Use the proposed MMR instead of directly adding neighborhood and point-wise maps (ablation) | RIENet · ModelNet40 | MAE(R): 0.0072 -> 0.0033 | Helped |
| Use a 1×3 rather than 1×1 convolution kernel for IE message propagation (ablation) | RIENet · ModelNet40 Gaussian noise | MAE(R): 0.0294 -> 0.0069 | Helped |
Closest papers by meaning
- Inlier Confidence Calibration for Point Cloud Registration (CVPR 2024 · similarity 0.94)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.93)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.88)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · similarity 0.87)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.87)
- HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration (CVPR 2025 · 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.