Compositional Human Pose Regression

Abstract

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.

Accepted by International Conference on Computer Vision (ICCV) 2017

Cited by in corpus (24)

• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• TFPose: Direct Human Pose Estimation with Transformers
• Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
• 3D Human Pose Estimation with Relational Networks
• Video Based Reconstruction of 3D People Models
• Learning to Estimate 3D Human Pose and Shape from a Single Color Image
• SMPLR: Deep SMPL reverse for 3D human pose and shape recovery
• Integral Human Pose Regression
• GraFormer: Graph Convolution Transformer for 3D Pose Estimation
• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video
• DRPose3D: Depth Ranking in 3D Human Pose Estimation
• An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge
• Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization
• Learning 3D Human Pose from Structure and Motion
• 3D Human Pose Estimation with 2D Marginal Heatmaps
• Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
• Human Motion Analysis with Deep Metric Learning
• Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation
• Ordinal Depth Supervision for 3D Human Pose Estimation
• Dense 3D Regression for Hand Pose Estimation
• Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
• PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
• View Invariant 3D Human Pose Estimation
• Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks