mlsanityData to 14 Oct 2026

Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning

arXiv 2306.11406 ↗First posted 20 Jun 2023cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 59 of its 150 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

59 of 150 references.

References · 59

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2020Point Transformercited by 1,470
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  8. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  10. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  11. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  12. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
38 more
  1. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  2. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  3. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  4. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  5. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  6. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  7. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  8. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 61
  9. 2020Future Video Synthesis with Object Motion Predictioncited by 57
  10. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  11. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  12. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  13. 2022Learning Debiased Classifier with Biased Committeecited by 51
  14. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  15. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  16. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  17. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  18. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
  19. 2020Weakly-supervised 3D Shape Completion in the Wildcited by 33
  20. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  21. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  22. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  23. 20193D-Rotation-Equivariant Quaternion Neural Networkscited by 30
  24. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  25. 2020Learning to Orient Surfaces by Self-supervised Spherical CNNscited by 26
  26. 2020High-dimensional Convolutional Networks for Geometric Pattern Recognitioncited by 24
  27. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  28. 2021Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learningcited by 19
  29. 2022PeRFception: Perception using Radiance Fieldscited by 19
  30. 2021HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challengecited by 17
  31. 2022Shape-Pose Disentanglement using SE(3)-equivariant Vector Neuronscited by 16
  32. 2023Instant Domain Augmentation for LiDAR Semantic Segmentationcited by 16
  33. 2020Triangle-Net: Towards Robustness in Point Cloud Learningcited by 13
  34. 2020Combinatorial 3D Shape Generation via Sequential Assemblycited by 13
  35. 2022A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learningcited by 10
  36. 2021Deep Virtual Markers for Articulated 3D Shapescited by 7
  37. 2016Refining Geometry from Depth Sensors using IR Shading Imagescited by 5
  38. 2022Learning to Register Unbalanced Point Pairscited by 5

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

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

3 papers.

  1. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  2. 2025Combinative Matching for Geometric Shape Assemblycited by 3
  3. 2024Symmetry-Robust 3D Orientation Estimationcited by 1