mlsanityData to 7 Oct 2026

Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows

arXiv 2003.10350 ↗First posted 23 Mar 2020cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes. In this paper we present practical semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions that support self-supervised learning. In extensive experiments using 3D motion capture datasets like CMU, Human3.6M, 3DPW, or AMASS, as well as image repositories like COCO, we show that the proposed methods outperform the state of the art, supporting the practical construction of an accurate family of models based on large-scale training with diverse and incompletely labeled image and video data.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 20; 2023: 21; 2024: 14; 2025: 4; 2026: 3.

94 papers.

Sort:

By area:

  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  3. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  5. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  6. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  7. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  8. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  9. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  10. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  11. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  12. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
38 more
  1. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  2. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  3. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 102
  4. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  5. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  6. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  7. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  8. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  9. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  10. 2023X-Avatar: Expressive Human Avatarscited by 66
  11. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  12. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  13. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
  14. 2022BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Informationcited by 51
  15. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  16. 2022Accurate 3D Body Shape Regression using Metric and Semantic Attributescited by 49
  17. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 46
  18. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  19. 2023BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesiscited by 44
  20. 2023Generative Proxemics: A Prior for 3D Social Interaction from Imagescited by 43
  21. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  22. 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
  23. 2021Adversarial Parametric Pose Priorcited by 38
  24. 2022Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Videocited by 37
  25. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  26. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  27. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 33
  28. 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
  29. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  30. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
  31. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  32. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  33. 2022SUPR: A Sparse Unified Part-Based Human Representationcited by 21
  34. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  35. 2021Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulationcited by 19
  36. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  37. 2023HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observationscited by 17
  38. 2024Synergistic Global-space Camera and Human Reconstruction from Videoscited by 17

50 most cited of 94 All 94 (JSON)