Papers › Leveraging Inlier Correspondences Proportion for Point Cloud Registration
Leveraging Inlier Correspondences Proportion for Point Cloud Registration
Lifa Zhu, Haining Guan, Changwei Lin, Renmin Han
In feature-learning based point cloud registration, the correct correspondence construction is vital for the subsequent transformation estimation. However, it is still a challenge to extract discriminative features from point cloud, especially when the input is partial and composed by indistinguishable surfaces (planes, smooth surfaces, etc.). As a result, the proportion of inlier correspondences that precisely match points between two unaligned point clouds is beyond satisfaction. Motivated by this, we devise several techniques to promote feature-learning based point cloud registration performance by leveraging inlier correspondences proportion: a pyramid hierarchy decoder to characterize point features in multiple scales, a consistent voting strategy to maintain consistent correspondences and a geometry guided encoding module to take geometric characteristics into consideration. Based on the above techniques, We build our Geometry-guided Consistent Network (GCNet), and challenge GCNet by indoor, outdoor and object-centric synthetic datasets. Comprehensive experiments demonstrate that GCNet outperforms the state-of-the-art methods and the techniques used in GCNet is model-agnostic, which could be easily migrated to other feature-based deep learning or traditional registration methods, and dramatically improve the performance. The code is available at https://github.com/zhulf0804/NgeNet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Point Cloud Registration | 3DLoMatch (10-30% overlap) | NgeNet | Recall ( correspondence RMSE below 0.2) | 71.9 | #3 of 13 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | NgeNet | RE (all) | 4.932 | #1 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | NgeNet | Recall (0.3m, 15 degrees) | 95.0 | #1 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | NgeNet | TE (all) | 0.155 | #1 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - sample 5k interest points) | NgeNet | Recall ( correspondence RMSE below 0.2) | 92.9 | #1 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections