mlsanityData to 14 Oct 2026

SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data

arXiv 2308.05410 ↗First posted 10 Aug 2023cs.CV cs.GR cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper proposes a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated. Our proposed model adheres to the following principles: i) keypoints inference is fully unsupervised (no annotation given), ii) keypoints position error should be low and resilient to PCD perturbations (robustness), iii) keypoints should not change their indexes for the intra-class objects (semantic coherence), iv) keypoints should be close to or proximal to PCD surface (compactness). We achieve these desiderata by proposing a new self-supervised training strategy for keypoints estimation that does not assume any a priori knowledge of the object class, and a model architecture with coupled auxiliary losses that promotes the desired keypoints properties. We compare the keypoints estimated by the proposed approach with those of the state-of-the-art unsupervised approaches. The experiments show that our approach outperforms by estimating keypoints with improved coverage (+9.41%) while being semantically consistent (+4.66%) that best characterizes the object's 3D shape for downstream tasks. Code and data are available at: https://github.com/IITPAVIS/SC3K

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 10 Aug 2023.

Builds on

31 of 47 references.

References · 31

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015Fast R-CNNcited by 2,933
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2018PCN: Point Completion Networkcited by 384
  6. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  7. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  8. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  9. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  10. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  11. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  12. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
19 more
  1. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  2. 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 51
  3. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 51
  4. 2020Unsupervised Learning of Intrinsic Structural Representation Pointscited by 39
  5. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  6. 2021Skeleton Merger: an Unsupervised Aligned Keypoint Detectorcited by 27
  7. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  8. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  9. 2022USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulationcited by 27
  10. 2020Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Setscited by 23
  11. 2021Learning 3D Dense Correspondence via Canonical Point Autoencodercited by 21
  12. 2020UKPGAN: A General Self-Supervised Keypoint Detectorcited by 15
  13. 2021OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrievalcited by 12
  14. 2022SNAKE: Shape-aware Neural 3D Keypoint Fieldcited by 10
  15. 2022Unsupervised Point Cloud Pre-Training via Contrasting and Clusteringcited by 9
  16. 2020Self-supervised Point Set Local Descriptors for Point Cloud Registrationcited by 7
  17. 2021Task-Aware Sampling Layer for Point-Wise Analysiscited by 6
  18. 2022Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstructioncited by 5
  19. 2022Prototype-Aware Heterogeneous Task for Point Cloud Completioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 3.

9 papers.

  1. 2024Point2SSM++: Self-Supervised Learning of Anatomical Shape Models from Point Cloudscited by 5
  2. 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Featurescited by 5
  3. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  4. 2024SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapescited by 1
  5. 2025PAOLI: Pose-free Articulated Object Learning from Sparse-view Imagescited by 1
  6. 2025KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Modelscited by 0
  7. 2026SCALP: Semi-Supervised Statistical Shape Modeling from Imperfect 3D Photogrammetry via Landmark-Anchored Spectral Warpcited by 0
  8. 2026TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photographycited by 0
  9. 2026KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalizationcited by 0