mlsanityData to 14 Oct 2026

Skeleton Merger: an Unsupervised Aligned Keypoint Detector

arXiv 2103.10814 ↗First posted 19 Mar 2021cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of keypoint itself. Meanwhile, current unsupervised detectors are unable to generate aligned keypoints with good coverage. In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects. It is based on an Autoencoder architecture. The encoder proposes keypoints and predicts activation strengths of edges between keypoints. The decoder performs uniform sampling on the skeleton and refines it into small point clouds with pointwise offsets. Then the activation strengths are applied and the sub-clouds are merged. Composite Chamfer Distance (CCD) is proposed as a distance between the input point cloud and the reconstruction composed of sub-clouds masked by activation strengths. We demonstrate that Skeleton Merger is capable of detecting semantically-rich salient keypoints with good alignment, and shows comparable performance to supervised methods on the KeypointNet dataset. It is also shown that the detector is robust to noise and subsampling. Our code is available at https://github.com/eliphatfs/SkeletonMerger.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

15 of 34 references.

References · 15

  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. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  6. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  7. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  8. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  9. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  10. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
  11. 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 51
  12. 2020Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Setscited by 23
3 more
  1. 2016Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputscited by 9
  2. 2018Performance Evaluation of 3D Correspondence Grouping Algorithmscited by 4
  3. 20133D Interest Point Detection via Discriminative Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 7; 2024: 6; 2025: 4; 2026: 3.

27 papers.

Sort:

By area:

  1. 2022Skeleton-free Pose Transfer for Stylized 3D Characterscited by 30
  2. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  3. 2022USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulationcited by 27
  4. 2023ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environmentcited by 23
  5. 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 23
  6. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  7. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 13
  8. 2021Localization with Sampling-Argmaxcited by 11
  9. 2023ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touchcited by 11
  10. 2024ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robotscited by 11
  11. 2023SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Datacited by 9
  12. 2023SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registrationcited by 9
15 more
  1. 2021Object Wake-up: 3D Object Rigging from a Single Imagecited by 8
  2. 2022Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstructioncited by 5
  3. 2024General-purpose Clothes Manipulation with Semantic Keypointscited by 5
  4. 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Featurescited by 5
  5. 2024ESCAPE: Equivariant Shape Completion via Anchor Point Encodingcited by 4
  6. 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulationcited by 2
  7. 2022Semantic keypoint extraction for scanned animals using multi-depth-camera systemscited by 1
  8. 20233D Keypoint Estimation Using Implicit Representation Learningcited by 1
  9. 2024SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapescited by 1
  10. 2025CLASP: General-Purpose Clothes Manipulation with Semantic Keypointscited by 1
  11. 2025FCBV-Net: Category-Level Robotic Garment Smoothing via Feature-Conditioned Bimanual Value Predictioncited by 0
  12. 2025Skeleton-based Robust Registration Framework for Corrupted 3D Point Cloudscited by 0
  13. 2025KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Modelscited by 0
  14. 2026Learned Suppression for 3D Keypoint Detection with a Graph-Transformer Backbonecited by 0
  15. 2026KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalizationcited by 0