mlsanityData to 7 Oct 2026

KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations

arXiv 2002.12687 ↗First posted 28 Feb 2020cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 103,450 keypoints and 8,234 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset. Our code and data are available on https://github.com/qq456cvb/KeypointNet.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 10; 2024: 6; 2025: 6; 2026: 6.

50 papers.

Sort:

By area:

  1. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  2. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  3. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 50
  4. 2023FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Modelscited by 47
  5. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 42
  6. 2021Skeleton Merger: an Unsupervised Aligned Keypoint Detectorcited by 27
  7. 2022Affordance Learning from Play for Sample-Efficient Policy Learningcited 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. 2024Position: Measure Dataset Diversity, Don't Just Claim Itcited by 26
  11. 2021Learning 3D Dense Correspondence via Canonical Point Autoencodercited by 21
  12. 2021CoCoNets: Continuous Contrastive 3D Scene Representationscited by 19
38 more
  1. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  2. 2023Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Featurescited by 17
  3. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  4. 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimationcited by 12
  5. 2021Localization with Sampling-Argmaxcited by 11
  6. 2023Understanding Physical Dynamics with Counterfactual World Modelingcited by 11
  7. 2022SNAKE: Shape-aware Neural 3D Keypoint Fieldcited by 10
  8. 2023SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Datacited by 9
  9. 2021Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlasescited by 7
  10. 2021Task-Aware Sampling Layer for Point-Wise Analysiscited by 6
  11. 2022Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypointscited by 6
  12. 2022Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstructioncited by 5
  13. 2023Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistencycited by 5
  14. 2026PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understandingcited by 5
  15. 2023CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Framecited by 4
  16. 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Featurescited by 4
  17. 2022Learning Markerless Robot-Depth Camera Calibration and End-Effector Pose Estimationcited by 3
  18. 2023Semantic-Aware Implicit Template Learning via Part Deformation Consistencycited by 3
  19. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  20. 2024ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Modelscited by 3
  21. 2021Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Enginecited by 2
  22. 2022Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objectscited by 2
  23. 2025GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizationscited by 2
  24. 2022Semantic keypoint extraction for scanned animals using multi-depth-camera systemscited by 1
  25. 20233D Keypoint Estimation Using Implicit Representation Learningcited by 1
  26. 2025Channel-adaptive Cross-modal Generative Semantic Communication for Point Cloud Transmissioncited by 1
  27. 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updatescited by 1
  28. 2021Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlasescited by 0
  29. 2023AEPnP: A Less-constrained EPnP Solver for Pose Estimation with Anisotropic Scalingcited by 0
  30. 2024Variable Rate Neural Compression for Sparse Detector Datacited by 0
  31. 2025Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Trackscited by 0
  32. 2025KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Modelscited by 0
  33. 2025Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challengecited by 0
  34. 2026LmPT: Conditional Point Transformer for Anatomical Landmark Detection on 3D Point Cloudscited by 0
  35. 2026Learned Suppression for 3D Keypoint Detection with a Graph-Transformer Backbonecited by 0
  36. 2026Category-Level 3D Correspondence in Camera Space via Morphable Object Priorscited by 0
  37. 2026GenSP: Consistent Spherical Parameterization via Learning Shape Generative Modelscited by 0
  38. 2026Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Modelscited by 0