mlsanityData to 7 Oct 2026

Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration

arXiv 2211.16301 ↗First posted 29 Nov 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning universal representations across different applications domain is an open research problem. In fact, finding universal architecture within the same application but across different types of datasets is still unsolved problem too, especially in applications involving processing 3D point clouds. In this work we experimentally test several state-of-the-art learning-based methods for 3D point cloud registration against the proposed non-learning baseline registration method. The proposed method either outperforms or achieves comparable results w.r.t. learning based methods. In addition, we propose a dataset on which learning based methods have a hard time to generalize. Our proposed method and dataset, along with the provided experiments, can be used in further research in studying effective solutions for universal representations. Our source code is available at: github.com/DavidBoja/greedy-grid-search.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 76 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

36 of 76 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  3. 2017Exploring Generalization in Deep Learningcited by 595
  4. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  5. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  6. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  7. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  8. 2020Deep Global Registrationcited by 228
  9. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  10. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  11. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  12. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 175
24 more
  1. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  2. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  3. 2017Generalization in Deep Learningcited by 146
  4. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  5. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  6. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 141
  7. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 108
  8. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 100
  9. 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 96
  10. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  11. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  12. 2021A comprehensive survey on point cloud registrationcited by 84
  13. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
  14. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  15. 2019PCRNet: Point Cloud Registration Network using PointNet Encodingcited by 63
  16. 2021OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registrationcited by 50
  17. 2017Learning Compact Geometric Featurescited by 45
  18. 2014Learning Spatiotemporal Features with 3D Convolutional Networkscited by 43
  19. 2013Rotational Projection Statistics for 3D Local Surface Description and Object Recognitioncited by 36
  20. 2020Distinctive 3D local deep descriptorscited by 21
  21. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20
  22. 2017AA-ICP: Iterative Closest Point with Anderson Accelerationcited by 17
  23. 2018Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registrationcited by 7
  24. 2020StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networkscited by 1

Built on by

Not cited yet.