Integral Human Pose Regression
Not on the map. Why?
Abstract (arXiv)
State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.
Key facts. Cited by 255 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Nov 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 74; 2022: 61; 2023: 54; 2024: 33; 2025: 17; 2026: 16.
255 papers.
Sort:
By area:
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
- 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
- 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
- 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
- 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
- 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
- 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
- 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
38 more
- 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
- 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
- 2021Pose Recognition with Cascade Transformerscited by 99
- 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
- 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
- 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
- 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
- 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
- 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
- 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
- 2021DG-Font: Deformable Generative Networks for Unsupervised Font Generationcited by 70
- 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
- 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
- 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
- 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
- 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 58
- 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
- 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
- 2023PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulationcited by 56
- 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
- 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
- 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
- 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
- 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
- 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
- 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
- 2021Body Meshes as Pointscited by 45
- 2023Human Pose as Compositional Tokenscited by 45
- 20233D Human Mesh Estimation from Virtual Markerscited by 44
- 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
- 2023Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shapecited by 43
- 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
- 2023I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactionscited by 42
- 2021SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videoscited by 40
- 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
- 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 39
- 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
- 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
50 most cited of 255 All 255 (JSON)
- 2026KAD-Net: Kinematics-Aware Decoupled Learning for Robust 3D Hand Pose Estimation from a Single Depth Image11 Sep 2026
- 2026HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion20 Aug 2026
- 2026Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction10 Aug 2026
- 2026RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement26 Jun 2026
- 2026ActionMap: Robot Policy Learning via Voxel Action Heatmap5 Jun 2026
- 2026Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images5 Jun 2026
- 2026STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets21 May 2026
- 2026Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System20 May 2026
- 2026L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation9 May 2026
- 20262D Pre-Training for 3D Pose Estimation19 Apr 2026
- 2026MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement29 Mar 2026
- 2026PCFEx: Point Cloud Feature Extraction for Graph Neural Networks9 Mar 2026
38 more
- 2026UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing25 Feb 2026
- 2026SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models10 Feb 2026
- 2026Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation2 Feb 2026
- 2026BBoxMaskPose v2: Expanding Mutual Conditioning to 3D21 Jan 2026
- 2025PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation18 Dec 2025
- 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation16 Dec 2025
- 2025Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation11 Nov 2025
- 2025PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation24 Aug 2025
- 2025KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video28 Jul 2025
- 2025A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba26 Jul 2025
- 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors16 Jul 2025
- 2025Geometric-Guided Few-Shot Dental Landmark Detection with Human-Centric Foundation Model7 Jul 2025
- 2025Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance23 May 2025
- 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation17 May 2025
- 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformer12 May 2025
- 2025Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation4 May 2025
- 2025FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video29 Mar 2025
- 2025Reconstructing Humans with a Biomechanically Accurate Skeleton27 Mar 2025
- 2025HORT: Monocular Hand-held Objects Reconstruction with Transformers27 Mar 2025
- 2025RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformer16 Feb 2025
- 2025L3D-Pose: Lifting Pose for 3D Avatars from a Single Camera in the Wild2 Jan 2025
- 2024Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation27 Dec 2024
- 2024CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty11 Dec 2024
- 2024ProbPose: A Probabilistic Approach to 2D Human Pose Estimation3 Dec 2024
- 2024X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation20 Nov 2024
- 2024Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis5 Oct 2024
- 2024V-Hands: Touchscreen-based Hand Tracking for Remote Whiteboard Interaction20 Sep 2024
- 2024Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB17 Sep 2024
- 2024LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation31 Aug 2024
- 2024ViMo: Generating Motions from Casual Videos13 Aug 2024
- 2024Flexible graph convolutional network for 3D human pose estimation26 Jul 2024
- 2024Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment19 Jul 2024
- 2024TCFormer: Visual Recognition via Token Clustering Transformer16 Jul 2024
- 2024RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation11 Jul 2024
- 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation10 Jul 2024
- 2024V-VIPE: Variational View Invariant Pose Embedding9 Jul 2024
- 2024Human Modelling and Pose Estimation Overview27 Jun 2024
- 2024MLPHand: Real Time Multi-View 3D Hand Mesh Reconstruction via MLP Modeling23 Jun 2024
50 newest of 255 All 255 (JSON)
- 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoisercited by 13
- 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimatorscited by 4
- 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
- 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priorscited by 0
- 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors16 Jul 2025
- 2024CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators27 May 2024
- 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation27 May 2024
- 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser7 Mar 2024
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
- 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
- 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
- 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
- 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
- 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
- 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
- 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
12 most cited of 247 All 247 (JSON)
- 2026KAD-Net: Kinematics-Aware Decoupled Learning for Robust 3D Hand Pose Estimation from a Single Depth Image11 Sep 2026
- 2026HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion20 Aug 2026
- 2026Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction10 Aug 2026
- 2026RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement26 Jun 2026
- 2026Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images5 Jun 2026
- 2026STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets21 May 2026
- 2026Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System20 May 2026
- 2026L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation9 May 2026
- 20262D Pre-Training for 3D Pose Estimation19 Apr 2026
- 2026MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement29 Mar 2026
- 2026PCFEx: Point Cloud Feature Extraction for Graph Neural Networks9 Mar 2026
- 2026UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing25 Feb 2026
12 newest of 247 All 247 (JSON)