mlsanityData to 14 Oct 2026

Progressive Multi-view Human Mesh Recovery with Self-Supervision

arXiv 2212.05223 ↗First posted 10 Dec 2022cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor generalization performance to new settings, largely due to the limited diversity of image-mesh pairs in multi-view training data. To address this shortcoming, people have explored the use of synthetic images. But besides the usual impact of visual gap between rendered and target data, synthetic-data-driven multi-view estimators also suffer from overfitting to the camera viewpoint distribution sampled during training which usually differs from real-world distributions. Tackling both challenges, we propose a novel simulation-based training pipeline for multi-view human mesh recovery, which (a) relies on intermediate 2D representations which are more robust to synthetic-to-real domain gap; (b) leverages learnable calibration and triangulation to adapt to more diversified camera setups; and (c) progressively aggregates multi-view information in a canonical 3D space to remove ambiguities in 2D representations. Through extensive benchmarking, we demonstrate the superiority of the proposed solution especially for unseen in-the-wild scenarios.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 53 of its 64 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

53 of 64 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Mask R-CNNcited by 7,277
  3. 2015Spatial Transformer Networkscited by 1,429
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  10. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  11. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  12. 2017Learning from Synthetic Humanscited by 359
38 more
  1. 2016Convolutional Pose Machinescited by 325
  2. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  3. 2017Integral Human Pose Regressioncited by 256
  4. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  5. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  6. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  7. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  8. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  9. 2019Learnable Triangulation of Human Posecited by 161
  10. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  11. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  12. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  13. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  14. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  15. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  16. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  17. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  18. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  19. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  20. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  21. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  22. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  23. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  24. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  25. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  26. 2021Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wildcited by 48
  27. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  28. 2021Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wildcited by 40
  29. 2019Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wildcited by 38
  30. 2015Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimationcited by 37
  31. 2016MoCap-guided Data Augmentation for 3D Pose Estimation in the Wildcited by 37
  32. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 33
  33. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  34. 2019Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Imagescited by 28
  35. 2021Generalizable Human Pose Triangulationcited by 24
  36. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  37. 2018Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capturecited by 17
  38. 2020SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Datacited by 17

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 6; 2025: 1.

9 papers.

  1. 2023High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decompositioncited by 18
  2. 2024MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysiscited by 14
  3. 2024Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluationcited by 9
  4. 2024UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cuescited by 6
  5. 2022Multi-person 3D pose estimation from unlabelled datacited by 2
  6. 2024SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformerscited by 2
  7. 2024Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Imagescited by 2
  8. 2024Self-learning Canonical Space for Multi-view 3D Human Pose Estimationcited by 0
  9. 2025Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Networkcited by 0