mlsanityData to 7 Oct 2026

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

arXiv 2011.00980 ↗First posted 2 Nov 2020cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering several plausible reconstructions compatible with the input data. We suggest that ambiguities can be modelled more effectively by parametrizing the possible body shapes and poses via a suitable 3D model, such as SMPL for humans. We propose to learn a multi-hypothesis neural network regressor using a best-of-M loss, where each of the M hypotheses is constrained to lie on a manifold of plausible human poses by means of a generative model. We show that our method outperforms alternative approaches in ambiguous pose recovery on standard benchmarks for 3D humans, and in heavily occluded versions of these benchmarks.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 15; 2024: 11; 2025: 1; 2026: 4.

50 papers.

Sort:

By area:

  1. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  2. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  3. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  4. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  5. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  6. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  7. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
  8. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  9. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  10. 2023Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shapecited by 43
  11. 2023Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Viewscited by 33
  12. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
38 more
  1. 2023Distribution-Aligned Diffusion for Human Mesh Recoverycited by 27
  2. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  3. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  4. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  5. 2023HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observationscited by 17
  6. 2021Coarse-to-fine Animal Pose and Shape Estimationcited by 16
  7. 2021Learning to Fit Morphable Modelscited by 16
  8. 2022Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Priorcited by 15
  9. 2023Rendering Humans from Object-Occluded Monocular Videoscited by 14
  10. 2023VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Spacecited by 13
  11. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humanscited by 13
  12. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 13
  13. 2022Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recoverycited by 12
  14. 2022Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learningcited by 12
  15. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  16. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  17. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  18. 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimizationcited by 6
  19. 2021DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimensioncited by 5
  20. 2024Distribution and Depth-Aware Transformers for 3D Human Mesh Recoverycited by 5
  21. 2024CondiMen: Conditional Multi-Person Mesh Recoverycited by 5
  22. 2021Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimationcited by 4
  23. 2023Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Inputcited by 4
  24. 2024CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inferencecited by 4
  25. 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimatorscited by 4
  26. 2024Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recoverycited by 4
  27. 2022Human Body Measurement Estimation with Adversarial Augmentationcited by 3
  28. 2023Multimodal Active Measurement for Human Mesh Recovery in Close Proximitycited by 2
  29. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  30. 2024CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertaintycited by 2
  31. 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recoverycited by 2
  32. 2023TAPE: Temporal Attention-based Probabilistic human pose and shape Estimationcited by 1
  33. 2023SHARE: Single-view Human Adversarial REconstructioncited by 0
  34. 2024A Simple Strategy for Body Estimation from Partial-View Imagescited by 0
  35. 2024Social EgoMesh Estimationcited by 0
  36. 2026Unsupervised SE(3) Disentanglement for in situ Macromolecular Morphology Identification from Cryo-Electron Tomographycited by 0
  37. 2026UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimationcited by 0
  38. 2026MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recoverycited by 0