Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
Not on the map. Why?
Abstract (arXiv)
Vision-based monocular human pose estimation, as one of the most fundamental and challenging problems in computer vision, aims to obtain posture of the human body from input images or video sequences. The recent developments of deep learning techniques have been brought significant progress and remarkable breakthroughs in the field of human pose estimation. This survey extensively reviews the recent deep learning-based 2D and 3D human pose estimation methods published since 2014. This paper summarizes the challenges, main frameworks, benchmark datasets, evaluation metrics, performance comparison, and discusses some promising future research directions.
Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 13; 2022: 15; 2023: 15; 2024: 8; 2025: 7; 2026: 1.
59 papers.
Sort:
By area:
- 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
- 2023Human Motion Generation: A Surveycited by 95
- 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
- 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
- 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
- 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
- 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
- 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
- 2025A Survey on Human Interaction Motion Generationcited by 25
- 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
- 20222D Human Pose Estimation: A Surveycited by 21
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
38 more
- 2021Lifting Monocular Events to 3D Human Posescited by 16
- 2024Large Language Model Benchmarks in Medical Taskscited by 16
- 2022Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directionscited by 14
- 2023A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perceptioncited by 13
- 2021Real-time RGBD-based Extended Body Pose Estimationcited by 12
- 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Camerascited by 12
- 2022PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Researchcited by 10
- 2021WildGait: Learning Gait Representations from Raw Surveillance Streamscited by 9
- 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
- 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
- 2024Markerless Multi-view 3D Human Pose Estimation: a surveycited by 9
- 2023Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environmentcited by 8
- 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detectioncited by 7
- 2022Privacy-Preserving In-Bed Pose Monitoring: A Fusion and Reconstruction Studycited by 6
- 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
- 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
- 2021Single Person Pose Estimation: A Surveycited by 4
- 2022Deep Multi-Task Networks For Occluded Pedestrian Pose Estimationcited by 4
- 2023CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Surveycited by 4
- 2022A survey of top-down approaches for human pose estimationcited by 3
- 2024DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesiscited by 3
- 2021Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networkscited by 2
- 2022Neural Sign Reenactor: Deep Photorealistic Sign Language Retargetingcited by 2
- 2023Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performancecited by 2
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensorscited by 2
- 2021Bottom-up approaches for multi-person pose estimation and it's applications: A brief reviewcited by 1
- 2022Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imagingcited by 1
- 2023AutoDepthNet: High Frame Rate Depth Map Reconstruction using Commodity Depth and RGB Camerascited by 1
- 2023TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chainscited by 1
- 2023Diffusion Models Enable Zero-Shot Pose Estimation for Lower-Limb Prosthetic Userscited by 1
- 2024Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipecited by 1
- 2025Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movementscited by 1
- 2025Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learningcited by 1
- 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Networkcited by 1
- 2021Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway Applicationscited by 0
- 2021Topology-Preserved Human Reconstruction with Detailscited by 0
- 2021Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?cited by 0
- 2021A3GC-IP: Attention-Oriented Adjacency Adaptive Recurrent Graph Convolutions for Human Pose Estimation from Sparse Inertial Measurementscited by 0
50 most cited of 59 All 59 (JSON)
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors17 Mar 2026
- 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network9 Oct 2025
- 2025Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning3 Oct 2025
- 2025Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities2 Oct 2025
- 20253D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review15 Sep 2025
- 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection23 Jun 2025
- 2025A Survey on Human Interaction Motion Generation17 Mar 2025
- 2025Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements5 Mar 2025
- 2024Yoga Pose Classification Using Transfer Learning29 Oct 2024
- 2024Large Language Model Benchmarks in Medical Tasks28 Oct 2024
- 2024DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis23 Sep 2024
- 2024Markerless Multi-view 3D Human Pose Estimation: a survey4 Jul 2024
38 more
- 2024Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe21 Jun 2024
- 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment15 Apr 2024
- 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Cameras26 Jan 2024
- 2024Real-Time Human Fall Detection using a Lightweight Pose Estimation Technique3 Jan 2024
- 2023Diffusion Models Enable Zero-Shot Pose Estimation for Lower-Limb Prosthetic Users13 Dec 2023
- 2023Pose Estimation and Tracking for ASIST30 Nov 2023
- 2023TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains6 Nov 2023
- 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey19 Oct 2023
- 2023Spike-based Neuromorphic Computing for Next-Generation Computer Vision15 Oct 2023
- 2023Unveiling the frontiers of deep learning: innovations shaping diverse domains6 Sep 2023
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Survey26 Aug 2023
- 2023Human Motion Generation: A Survey20 Jul 2023
- 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video12 Jul 2023
- 2023AutoDepthNet: High Frame Rate Depth Map Reconstruction using Commodity Depth and RGB Cameras24 May 2023
- 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models23 May 2023
- 2023Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance31 Mar 2023
- 2023A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception24 Mar 2023
- 2023Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment17 Jan 2023
- 2023CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey15 Jan 2023
- 2022Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions31 Dec 2022
- 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats29 Dec 2022
- 2022Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach21 Dec 2022
- 2022Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging15 Dec 2022
- 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving15 Dec 2022
- 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimation22 Nov 2022
- 2022Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting3 Sep 2022
- 2022Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation15 Jun 2022
- 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER30 May 2022
- 20222D Human Pose Estimation: A Survey15 Apr 2022
- 2022PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Research16 Mar 2022
- 2022Recovering 3D Human Mesh from Monocular Images: A Survey3 Mar 2022
- 2022Privacy-Preserving In-Bed Pose Monitoring: A Fusion and Reconstruction Study22 Feb 2022
- 2022A survey of top-down approaches for human pose estimation5 Feb 2022
- 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices28 Jan 2022
- 2021Bottom-up approaches for multi-person pose estimation and it's applications: A brief review22 Dec 2021
- 2021Learning to Regress Bodies from Images using Differentiable Semantic Rendering7 Oct 2021
- 2021Single Person Pose Estimation: A Survey21 Sep 2021
- 2021A3GC-IP: Attention-Oriented Adjacency Adaptive Recurrent Graph Convolutions for Human Pose Estimation from Sparse Inertial Measurements23 Jul 2021
50 newest of 59 All 59 (JSON)
- 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
- 2023Human Motion Generation: A Surveycited by 95
- 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
- 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
- 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
- 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
- 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
- 2025A Survey on Human Interaction Motion Generationcited by 25
- 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
- 20222D Human Pose Estimation: A Surveycited by 21
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
- 2021Lifting Monocular Events to 3D Human Posescited by 16
12 most cited of 57 All 57 (JSON)
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors17 Mar 2026
- 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network9 Oct 2025
- 2025Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities2 Oct 2025
- 20253D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review15 Sep 2025
- 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection23 Jun 2025
- 2025A Survey on Human Interaction Motion Generation17 Mar 2025
- 2025Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements5 Mar 2025
- 2024Yoga Pose Classification Using Transfer Learning29 Oct 2024
- 2024Large Language Model Benchmarks in Medical Tasks28 Oct 2024
- 2024DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis23 Sep 2024
- 2024Markerless Multi-view 3D Human Pose Estimation: a survey4 Jul 2024
- 2024Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe21 Jun 2024
12 newest of 57 All 57 (JSON)