mlsanityData to 7 Oct 2026

Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance

arXiv 2302.14268 ↗First posted 28 Feb 2023cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods, we present a novel self-supervised strategy that solves this problem without any human labels. Our key idea is to factorize canonical shapes and articulated object poses from input articulated shapes through part-level equivariant shape analysis. Specifically, we first introduce the concept of part-level SE(3) equivariance and devise a network to learn features of such property. Then, through a carefully designed fine-grained pose-shape disentanglement strategy, we expect that canonical spaces to support pose estimation could be induced automatically. Thus, we could further predict articulated object poses as per-part rigid transformations describing how parts transform from their canonical part spaces to the camera space. Extensive experiments demonstrate the effectiveness of our method on both complete and partial point clouds from synthetic and real articulated object datasets.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

33 of 38 references.

References · 33

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  3. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  7. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  8. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  9. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  10. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  11. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
21 more
  1. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  2. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  3. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  4. 2019CvxNet: Learnable Convex Decompositioncited by 173
  5. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  6. 2019Category-Level Articulated Object Pose Estimationcited by 158
  7. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  8. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  9. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  10. 2020Detailed 2D-3D Joint Representation for Human-Object Interactioncited by 93
  11. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  12. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  13. 2021Human Hands as Probes for Interactive Object Understandingcited by 51
  14. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  15. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  16. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  17. 2021GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completioncited by 41
  18. 2021Towards Real-World Category-level Articulation Pose Estimationcited by 39
  19. 2021Single-view robot pose and joint angle estimation via render & comparecited by 33
  20. 2020Neural Star Domain as Primitive Representationcited by 17
  21. 2021Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objectscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 8; 2025: 6; 2026: 4.

26 papers.

Sort:

By area:

  1. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  2. 2023An Outlook into the Future of Egocentric Visioncited by 84
  3. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  4. 2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 51
  5. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
  6. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  7. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  8. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  9. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 27
  10. 2023NAP: Neural 3D Articulation Priorcited by 25
  11. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  12. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 18
14 more
  1. 2025VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Videocited by 15
  2. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  3. 2023Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformationcited by 8
  4. 2024OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimationcited by 8
  5. 2026FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videoscited by 7
  6. 2025Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussianscited by 5
  7. 2024Approximately Piecewise E(3) Equivariant Point Networkscited by 4
  8. 2024SCANet: Correcting LEGO Assembly Errors with Self-Correct Assembly Networkcited by 3
  9. 2025DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Predictioncited by 2
  10. 2024Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimationcited by 1
  11. 2025Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splattingcited by 1
  12. 2026PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videoscited by 1
  13. 2026SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observationcited by 0
  14. 2026StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstructioncited by 0