mlsanityData to 14 Oct 2026

W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration

arXiv 2311.17460 ↗First posted 29 Nov 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Previous methods for 3D human motion recovery from monocular images often fall short due to reliance on camera coordinates, leading to inaccuracies in real-world applications. The limited availability and diversity of focal length labels further exacerbate misalignment issues in reconstructed 3D human bodies. To address these challenges, we introduce W-HMR, a weak-supervised calibration method that predicts "reasonable" focal lengths based on body distortion information, eliminating the need for precise focal length labels. Our approach enhances 2D supervision precision and recovery accuracy. Additionally, we present the OrientCorrect module, which corrects body orientation for plausible reconstructions in world space, avoiding the error accumulation associated with inaccurate camera rotation predictions. Our contributions include a novel weak-supervised camera calibration technique, an effective orientation correction module, and a decoupling strategy that significantly improves the generalizability and accuracy of human motion recovery in both camera and world coordinates. The robustness of W-HMR is validated through extensive experiments on various datasets, showcasing its superiority over existing methods. Codes and demos have been made available on the project page https://yw0208.github.io/w-hmr/.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 43 of its 62 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

43 of 62 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  11. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  12. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
31 more
  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  2. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  3. 2018Learning 3D Human Dynamics from Videocited by 316
  4. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  5. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  6. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  7. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  8. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  9. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  10. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  11. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  12. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  13. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  14. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  15. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  16. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  17. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  18. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  19. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  20. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  21. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  22. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  23. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81
  24. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  25. 2020Neural Descent for Visual 3D Human Pose and Shapecited by 60
  26. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 60
  27. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  28. 2019Learning 3D Human Shape and Pose from Dense Body Partscited by 48
  29. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  30. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  31. 2020Beyond Weak Perspective for Monocular 3D Human Pose Estimationcited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025From Camera to World: A Plug-and-Play Module for Human Mesh Transformationcited by 0
  2. 2026Monocular markerless biomechanics for clinically interpretable gait assessment in spinal cord injurycited by 0
  3. 2026A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamicscited by 0