mlsanityData to 14 Oct 2026

ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency

arXiv 2407.09862 ↗First posted 13 Jul 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent advances in point cloud registration mostly leverage geometric information. Although these methods have yielded promising results, they still struggle with problems of low overlap, thus limiting their practical usage. In this paper, we propose ML-SemReg, a plug-and-play point cloud registration framework that fully exploits semantic information. Our key insight is that mismatches can be categorized into two types, i.e., inter- and intra-class, after rendering semantic clues, and can be well addressed by utilizing multi-level semantic consistency. We first propose a Group Matching module to address inter-class mismatching, outputting multiple matching groups that inherently satisfy Local Semantic Consistency. For each group, a Mask Matching module based on Scene Semantic Consistency is then introduced to suppress intra-class mismatching. Benefit from those two modules, ML-SemReg generates correspondences with a high inlier ratio. Extensive experiments demonstrate excellent performance and robustness of ML-SemReg, e.g., in hard-cases of the KITTI dataset, the Registration Recall of MAC increases by almost 34 percentage points when our ML-SemReg is equipped. Code is available at urlhttps://github.com/Laka-3DV/ML-SemReg

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 63 references that are in the map. First posted on arXiv 13 Jul 2024.

Builds on

35 of 63 references.

References · 35

  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  3. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  4. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  5. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  6. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  7. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  8. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  9. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  10. 2020Deep Global Registrationcited by 229
  11. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  12. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
23 more
  1. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
  2. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  3. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  4. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 142
  5. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  6. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  7. 2021SuMa++: Efficient LiDAR-based Semantic SLAMcited by 100
  8. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  9. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 96
  10. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  11. 20233D Registration with Maximal Cliquescited by 84
  12. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 69
  13. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  14. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  15. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  16. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 42
  17. 2021Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Cloudscited by 23
  18. 2022PADLoC: LiDAR-Based Deep Loop Closure Detection and Registration Using Panoptic Attentioncited by 12
  19. 2023Segregator: Global Point Cloud Registration with Semantic and Geometric Cuescited by 11
  20. 2023G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Modelcited by 11
  21. 2023Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlapcited by 6
  22. 2022SARNet: Semantic Augmented Registration of Large-Scale Urban Point Cloudscited by 5
  23. 2023Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registrationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025TurboReg: TurboClique for Robust and Efficient Point Cloud Registrationcited by 13
  2. 20243D Registration in 30 Years: A Surveycited by 2
  3. 2026Unsupervised Point Cloud Registration via Training-Time Semantic Guidancecited by 0
  4. 2026MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Bufferscited by 0