Integral Human Pose Regression

2017/11/22 by Xiao Sun, Sun, Xiao, Bin Xiao +7 · 5 citations
Computer Science · #Advanced Vision and Imaging #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.1711.08229

openalex publication_date 2017/11/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Adam: A Method for Stochastic Optimization
• Generalized Procrustes Analysis
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• 3D Human Pose Estimation from a Single Image via Distance Matrix\n Regression
• Deformable Convolutional Networks
• Stacked Hourglass Networks for Human Pose Estimation
• 3D Human Pose Estimation = 2D Pose Estimation + Matching
• Xception: Deep Learning with Depthwise Separable Convolutions
• Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Learning Feature Pyramids for Human Pose Estimation
• A simple yet effective baseline for 3d human pose estimation
• Learning 3D Human Pose from Structure and Motion

Cited by

• PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation
• FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
• Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation
• PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation
• TFPose: Direct Human Pose Estimation with Transformers

Related

• Bias-Compensated Integral Regression for Human Pose Estimation
• Human Pose Regression by Combining Indirect Part Detection and\n Contextual Information
• An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge
• Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
• Human Pose Regression with Residual Log-likelihood Estimation