mlsanityData to 7 Oct 2026

Unsupervised Shape and Pose Disentanglement for 3D Meshes

arXiv 2007.11341 ↗First posted 22 Jul 2020cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation. Their key strength is the ability to factor surface variations into shape and pose dependent components. Learning such models requires lots of expert knowledge and hand-defined object-specific constraints, making the learning approach unscalable to novel objects. In this paper, we present a simple yet effective approach to learn disentangled shape and pose representations in an unsupervised setting. We use a combination of self-consistency and cross-consistency constraints to learn pose and shape space from registered meshes. We additionally incorporate as-rigid-as-possible deformation(ARAP) into the training loop to avoid degenerate solutions. We demonstrate the usefulness of learned representations through a number of tasks including pose transfer and shape retrieval. The experiments on datasets of 3D humans, faces, hands and animals demonstrate the generality of our approach. Code is made available at https://virtualhumans.mpi-inf.mpg.de/unsup_shape_pose/.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 10; 2023: 7; 2024: 12; 2025: 7; 2026: 4.

61 papers.

Sort:

By area:

  1. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  2. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  3. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  4. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 89
  5. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  6. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  7. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  8. 2022Neural Systematic Bindercited by 37
  9. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 36
  10. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  11. 20213D Pose Transfer with Correspondence Learning and Mesh Refinementcited by 30
  12. 2022Skeleton-free Pose Transfer for Stylized 3D Characterscited by 29
38 more
  1. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  2. 2022Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstructioncited by 21
  3. 2021Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfercited by 20
  4. 2024HUMOS: Human Motion Model Conditioned on Body Shapecited by 20
  5. 2021View Generalization for Single Image Textured 3D Modelscited by 19
  6. 2023Zero-shot Pose Transfer for Unrigged Stylized 3D Characterscited by 12
  7. 2023Weakly-supervised 3D Pose Transfer with Keypointscited by 12
  8. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  9. 2021AniFormer: Data-driven 3D Animation with Transformercited by 10
  10. 2021Geometry-Contrastive Transformer for Generalized 3D Pose Transfercited by 10
  11. 20223D Shape Sequence of Human Comparison and Classification using Current and Varifoldscited by 8
  12. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  13. 2025Category-Agnostic Neural Object Riggingcited by 8
  14. 2021A Riemannian Framework for Analysis of Human Body Surfacecited by 7
  15. 2021Intuitive Shape Editing in Latent Spacecited by 7
  16. 2024Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Imagescited by 7
  17. 2021Neural Human Deformation Transfercited by 6
  18. 2021LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodiescited by 6
  19. 2023Correspondence-free online human motion retargetingcited by 6
  20. 20233D Generative Model Latent Disentanglement via Local Eigenprojectioncited by 6
  21. 2024ShapeFusion: A 3D diffusion model for localized shape editingcited by 6
  22. 2024Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Posescited by 6
  23. 2024Temporal Residual Jacobians For Rig-free Motion Transfercited by 6
  24. 2021A structured latent space for human body motion generationcited by 5
  25. 2023HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargetingcited by 5
  26. 2025SMF: Template-free and Rig-free Animation Transfer using Kinetic Codescited by 5
  27. 2021Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapescited by 4
  28. 2024Towards Robust 3D Pose Transfer with Adversarial Learningcited by 4
  29. 2022Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglementcited by 3
  30. 2021Disentangling Geometric Deformation Spaces in Generative Latent Shape Modelscited by 2
  31. 2021Identity-Disentangled Neural Deformation Model for Dynamic Meshescited by 2
  32. 2022Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garmentcited by 2
  33. 2022Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentationcited by 2
  34. 2023MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learningcited by 2
  35. 2024DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domaincited by 2
  36. 2024DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Posecited by 2
  37. 2024JADE: Joint-aware Latent Diffusion for 3D Human Generative Modelingcited by 2
  38. 2026NeuROK: Generative 4D Neural Object Kinematicscited by 2

50 most cited of 61 All 61 (JSON)