Research map / Point clouds / Registration and matching
A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration
Li Yan, Pengcheng Wei, Hong Xie, Jicheng Dai, Hao Wu, Ming Da Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 optimal selection strategy (OSS) (ablation) | GROR · ETH Facade | running time (s): 0.035 -> 0.023 | Improved |
| add optimal selection strategy (OSS) (ablation) | GROR · WHU-TLS Heritage | running time (s): 0.549 -> 0.180 | Improved |
| add optimal selection strategy (OSS) (ablation) | GROR · ETH Trees | running time (s): 5.493 -> 1.617 | Improved |
| increase top-K reliable correspondences to K >= 800 (ablation) | GROR · ETH dataset | rotation and translation error | Improved |
| increase K from 100 to 1200 (ablation) | GROR · ETH dataset | running time | Hurt |
| increase downsampling size rho from 0.1 to 0.5 m | GROR · ETH dataset | registration accuracy | Hurt |
| use GROR instead of Gore | Gore · ETH Arch | running time (s): 65.53 -> 0.526 | Improved |
| use GROR instead of Teaser++ | Teaser++ · ETH Trees | running time (s): 17.41 -> 1.617 | Improved |
| use GROR instead of RANSAC | RANSAC · WHU-TLS Railway | rotation error (deg): 58.13 -> 0.055 | Improved |
| use GROR instead of FGR | FGR · ETH Trees | rotation error (deg): 127.0 -> 0.125 | Improved |
| use GROR instead of Gore | Gore · WHU-TLS Subway | rotation error (deg): 9.305 -> 0.496 | Improved |
| use GROR instead of FMP+BNB | FMP+BNB · WHU-TLS Subway | rotation error (deg): 0 -> 0.496 | Hurt |
Closest papers by meaning
- Guaranteed Outlier Removal for Point Cloud Registration with Correspondences (TPAMI 2017 · similarity 0.95)
- A Practical O(N2) Outlier Removal Method for Point Cloud Registration (TPAMI 2021 · similarity 0.93)
- Reliable Inlier Evaluation for Unsupervised Point Cloud Registration (AAAI 2022 · similarity 0.92)
- SC2-PCR++: Rethinking the Generation and Selection for Efficient and Robust Point Cloud Registration (TPAMI 2023 · similarity 0.92)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.92)
- Inlier Confidence Calibration for Point Cloud Registration (CVPR 2024 · similarity 0.90)
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.
