mlsanityData to 7 Oct 2026

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective

arXiv 2104.11536 ↗First posted 23 Apr 2021cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications. Recently, benefited from the deep learning technologies, a significant amount of research efforts have greatly advanced the monocular human pose estimation both in 2D and 3D areas. Although there have been some works to summarize the different approaches, it still remains challenging for researchers to have an in-depth view of how these approaches work. In this paper, we provide a comprehensive and holistic 2D-to-3D perspective to tackle this problem. We categorize the mainstream and milestone approaches since the year 2014 under unified frameworks. By systematically summarizing the differences and connections between these approaches, we further analyze the solutions for challenging cases, such as the lack of data, the inherent ambiguity between 2D and 3D, and the complex multi-person scenarios. We also summarize the pose representation styles, benchmarks, evaluation metrics, and the quantitative performance of popular approaches. Finally, we discuss the challenges and give deep thinking of promising directions for future research. We believe this survey will provide the readers with a deep and insightful understanding of monocular human pose estimation.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 156 of its 226 references that are in the map. First posted on arXiv 23 Apr 2021.

Builds on

156 of 226 references.

References · 156

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  10. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  12. 2017End-to-end Recovery of Human Shape and Posecited by 883
38 more
  1. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  2. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  4. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  5. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  7. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  9. 2017Learning from Synthetic Humanscited by 358
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2016Convolutional Pose Machinescited by 325
  13. 2018Learning 3D Human Dynamics from Videocited by 315
  14. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  15. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  16. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  17. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  18. 2017Integral Human Pose Regressioncited by 255
  19. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  20. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  21. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  22. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  23. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  24. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  25. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  26. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  27. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  28. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  29. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  30. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  31. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  32. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  33. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  34. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  35. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  36. 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 139
  37. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  38. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133

50 most cited of 156 All 156 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 15; 2023: 19; 2024: 8; 2025: 2; 2026: 2.

49 papers.

Sort:

By area:

  1. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  2. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  3. 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 113
  4. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  5. 2023Human Motion Generation: A Surveycited by 95
  6. 2022Capturing and Animation of Body and Clothing from Monocular Videocited by 83
  7. 2023Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenescited by 68
  8. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  9. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  10. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  11. 2023Parsing is All You Need for Accurate Gait Recognition in the Wildcited by 32
  12. 2022DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimationcited by 29
37 more
  1. 2025A Survey on Human Interaction Motion Generationcited by 25
  2. 2022Gait Recognition in the Wild with Multi-hop Temporal Switchcited by 22
  3. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  4. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  5. 2023Unsupervised Keypoints from Pretrained Diffusion Modelscited by 15
  6. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  7. 2022Large Scale Real-World Multi-Person Trackingcited by 14
  8. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  9. 2024Deep learning for 3D human pose estimation and mesh recovery: A surveycited by 11
  10. 2022PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Researchcited by 10
  11. 2023DisguisOR: Holistic Face Anonymization for the Operating Roomcited by 9
  12. 2024Markerless Multi-view 3D Human Pose Estimation: a surveycited by 9
  13. 2022MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognitioncited by 8
  14. 2021Learning Instance-level Spatial-Temporal Patterns for Person Re-identificationcited by 7
  15. 2023Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimationcited by 7
  16. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  17. 2022Delving into the Frequency: Temporally Consistent Human Motion Transfer in the Fourier Spacecited by 5
  18. 2022REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfercited by 4
  19. 2024Human Modelling and Pose Estimation Overviewcited by 4
  20. 2024Motion Capture from Inertial and Vision Sensorscited by 4
  21. 2026FMPose3D: monocular 3D pose estimation via flow matchingcited by 3
  22. 2023Semi-Automated Computer Vision based Tracking of Multiple Industrial Entities -- A Framework and Dataset Creation Approachcited by 2
  23. 2023Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementiacited by 2
  24. 2024NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Imagescited by 2
  25. 2022WOC: A Handy Webcam-based 3D Online Chatroomcited by 1
  26. 2023Elephants and Algorithms: A Review of the Current and Future Role of AI in Elephant Monitoringcited by 1
  27. 2023Iterative Graph Filtering Network for 3D Human Pose Estimationcited by 1
  28. 2023Spatio-temporal MLP-graph network for 3D human pose estimationcited by 1
  29. 2023Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Mapscited by 1
  30. 2024EPOCH: Jointly Estimating the 3D Pose of Cameras and Humanscited by 1
  31. 2024A vision-based framework for human behavior understanding in industrial assembly linescited by 1
  32. 20233D shape reconstruction of semi-transparent wormscited by 0
  33. 2023Augmenting Vision-Based Human Pose Estimation with Rotation Matrixcited by 0
  34. 2023Spatial Attention-based Distribution Integration Network for Human Pose Estimationcited by 0
  35. 2023Active headrest combined with a depth camera-based ear-positioning systemcited by 0
  36. 2025End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systemscited by 0
  37. 2026Topology-Unified 2D Pose Estimation across Intact, Residual and Prosthetic Limbscited by 0