mlsanityData to 7 Oct 2026

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos

arXiv 2103.09009 ↗First posted 16 Mar 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

The end-to-end Human Mesh Recovery (HMR) approach has been successfully used for 3D body reconstruction. However, most HMR-based frameworks reconstruct human body by directly learning mesh parameters from images or videos, while lacking explicit guidance of 3D human pose in visual data. As a result, the generated mesh often exhibits incorrect pose for complex activities. To tackle this problem, we propose to exploit 3D pose to calibrate human mesh. Specifically, we develop two novel Pose Calibration frameworks, i.e., Serial PC-HMR and Parallel PC-HMR. By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module. Furthermore, since the calibration module is designed via non-rigid pose transformation, our PC-HMR frameworks can flexibly tackle bone length variations to alleviate misplacement in the calibrated mesh. Finally, our frameworks are based on generic and complementary integration of data-driven learning and geometrical modeling. Via plug-and-play modules, they can be efficiently adapted for both image/video-based human mesh recovery. Additionally, they have no requirement of extra 3D pose annotations in the testing phase, which releases inference difficulties in practice. We perform extensive experiments on the popular bench-marks, i.e., Human3.6M, 3DPW and SURREAL, where our PC-HMR frameworks achieve the SOTA results.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 16 Mar 2021.

Builds on

32 of 42 references.

References · 32

  1. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  3. 2017End-to-end Recovery of Human Shape and Posecited by 883
  4. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  10. 2017Learning from Synthetic Humanscited by 358
  11. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  12. 2018Learning 3D Human Dynamics from Videocited by 315
20 more
  1. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  2. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  3. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  4. 2017Integral Human Pose Regressioncited by 255
  5. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  6. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  7. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  8. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  9. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  10. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  11. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  13. 2017Self-supervised Learning of Motion Capturecited by 97
  14. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  15. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  16. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  17. 2019Predicting 3D Human Dynamics from Videocited by 51
  18. 2019Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wildcited by 38
  19. 2020Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimationcited by 36
  20. 2018Cascaded Pyramid Network for 3D Human Pose Estimation Challengecited by 1

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 6; 2024: 9; 2025: 5.

25 papers.

Sort:

By area:

  1. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  2. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  3. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  4. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  5. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  6. 2023High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decompositioncited by 18
  7. 2023Language-guided Human Motion Synthesis with Atomic Actionscited by 17
  8. 2023Full-dose Whole-body PET Synthesis from Low-dose PET Using High-efficiency Denoising Diffusion Probabilistic Model: PET Consistency Modelcited by 15
  9. 2024MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysiscited by 14
  10. 2024IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generationcited by 11
  11. 2024AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-maskingcited by 10
  12. 2024Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluationcited by 9
13 more
  1. 2022The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimationcited by 8
  2. 2025dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysiscited by 8
  3. 2024FSC: Few-point Shape Completioncited by 6
  4. 2023GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Posecited by 4
  5. 2024ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videoscited by 4
  6. 2025PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generationcited by 4
  7. 2024DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesiscited by 3
  8. 2021Pose-guided Generative Adversarial Net for Novel View Action Synthesiscited by 1
  9. 2023CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationshipscited by 1
  10. 2024Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Imagescited by 1
  11. 20253D Human Mesh Estimation from Single View RGBDcited by 0
  12. 2025SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluationcited by 0
  13. 2025Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Networkcited by 0