mlsanityData to 7 Oct 2026

Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects

arXiv 2110.04411 ↗First posted 8 Oct 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent part parsing. In this paper, we propose PPD (unsupervised Pose-aware Part Decomposition) to address a novel setting that explicitly targets man-made articulated objects with mechanical joints, considering the part poses. We show that category-common prior learning for both part shapes and poses facilitates the unsupervised learning of (1) part decomposition with non-primitive-based implicit representation, and (2) part pose as joint parameters under single-frame shape supervision. We evaluate our method on synthetic and real datasets, and we show that it outperforms previous works in consistent part parsing of the articulated objects based on comparable part pose estimation performance to the supervised baseline.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

36 of 49 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Layer Normalizationcited by 5,579
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  8. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  9. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  10. 2017End-to-end Recovery of Human Shape and Posecited by 883
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  12. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
24 more
  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  2. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  4. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  5. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  6. 2019CvxNet: Learnable Convex Decompositioncited by 173
  7. 2019Category-Level Articulated Object Pose Estimationcited by 158
  8. 2019NASA: Neural Articulated Shape Approximationcited by 149
  9. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  10. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  11. 2019Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"cited by 106
  12. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  13. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  14. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  15. 2020Articulation-aware Canonical Surface Mappingcited by 80
  16. 2018Deep Part Induction from Articulated Object Pairscited by 66
  17. 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 66
  18. 2018Im2Struct: Recovering 3D Shape Structure from a Single RGB Imagecited by 55
  19. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  20. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  21. 2018The RBO Dataset of Articulated Objects and Interactionscited by 34
  22. 2019StructEdit: Learning Structural Shape Variationscited by 23
  23. 2020Neural Star Domain as Primitive Representationcited by 17
  24. 2016Scene Flow Estimation: A Surveycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 6; 2024: 0; 2025: 2; 2026: 1.

12 papers.

  1. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  2. 2023Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Cloudscited by 34
  3. 2023Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariancecited by 26
  4. 2023NAP: Neural 3D Articulation Priorcited by 25
  5. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  6. 20213D Compositional Zero-shot Learning with DeCompositional Consensuscited by 16
  7. 2025VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Videocited by 15
  8. 2023Semi-Weakly Supervised Object Kinematic Motion Predictioncited by 14
  9. 2022Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collectionscited by 13
  10. 2023MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Fieldcited by 12
  11. 2026GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splattingcited by 1
  12. 2022Recognition of All Categories of Entities by AIcited by 0