mlsanityData to 13 Oct 2026

PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration

arXiv 2609.25375 ↗First posted 21 Sep 2026cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers. Planar regions are particularly difficult for conventional point descriptors and are therefore often suppressed or discarded before matching. We present PARTE (Plane-Assisted Robust Transformation Estimation), a global registration method that instead treats planar structure as complementary registration evidence. PARTE extracts planar patches and represents them using our novel Plane Context Histogram (PCH), a descriptor that encodes the geometry surrounding each patch, while a two-level matching procedure identifies reliable plane correspondences. Candidate point and plane correspondences are combined in a confidence-weighted compatibility graph for joint outlier rejection, followed by rigid transformation estimation. When no usable plane correspondences are available, PARTE naturally reduces to point-only registration. We evaluate PARTE on 8,097 registration pairs across six indoor and outdoor benchmarks spanning dense RGB-D and sparse LiDAR measurements. Evaluations show PARTE achieves the highest overall success rate against 13 standard and state-of-the-art methods while maintaining low runtime. An open-source C++ implementation with Python bindings is provided at https://ariarobotics.github.io/parte/.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 33 of its 83 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

33 of 83 references.

References · 33

  1. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 334
  2. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 288
  3. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  4. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 176
  5. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  6. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 142
  7. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  8. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  9. 2019Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejectioncited by 93
  10. 20233D Registration with Maximal Cliquescited by 84
  11. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 83
  12. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
21 more
  1. 2016SegMatch: Segment based loop-closure for 3D point cloudscited by 48
  2. 2020ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariantscited by 38
  3. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  4. 2017SegICP: Integrated Deep Semantic Segmentation and Pose Estimationcited by 29
  5. 2020CLIPPER: A Graph-Theoretic Framework for Robust Data Associationcited by 28
  6. 2020RGB-D SLAM with Structural Regularitiescited by 19
  7. 2022A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environmentscited by 19
  8. 2023Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAMcited by 18
  9. 2021RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration using Invariant Compatibilitycited by 16
  10. 2024KISS-Matcher: Fast and Robust Point Cloud Registration Revisitedcited by 16
  11. 2020Adaptive Robust Kernels for Non-Linear Least Squares Problemscited by 13
  12. 2022TRAVEL: Traversable Ground and Above-Ground Object Segmentation Using Graph Representation of 3D LiDAR Scanscited by 11
  13. 2023G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Modelcited by 11
  14. 2018PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstructioncited by 8
  15. 2022VIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAMcited by 7
  16. 2024RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registrationcited by 7
  17. 2021DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratioscited by 5
  18. 2022SARNet: Semantic Augmented Registration of Large-Scale Urban Point Cloudscited by 5
  19. 2024CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registrationcited by 5
  20. 2024FracGM: A Fast Fractional Programming Technique for Geman-McClure Robust Estimatorcited by 3
  21. 2020Plane Pair Matching for Efficient 3D View Registrationcited by 1

Built on by

Not cited yet.