RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation

Abstract

We propose a novel efficient and lightweight model for human pose estimation from a single image. Our model is designed to achieve competitive results at a fraction of the number of parameters and computational cost of various state-of-the-art methods. To this end, we explicitly incorporate part-based structural and geometric priors in a hierarchical prediction framework. At the coarsest resolution, and in a manner similar to classical part-based approaches, we leverage the kinematic structure of the human body to propagate convolutional feature updates between the keypoints or body parts. Unlike classical approaches, we adopt end-to-end training to learn this geometric prior through feature updates from data. We then propagate the feature representation at the coarsest resolution up the hierarchy to refine the predicted pose in a coarse-to-fine fashion. The final network effectively models the geometric prior and intuition within a lightweight deep neural network, yielding state-of-the-art results for a model of this size on two standard datasets, Leeds Sports Pose and MPII Human Pose.

References in corpus (8)

• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Stacked Hourglass Networks for Human Pose Estimation
• DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
• Multi-Context Attention for Human Pose Estimation
• Differentiable Dynamic Programming for Structured Prediction and Attention
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• Fast Human Pose Estimation

Cited by in corpus (3)

• Relation-Based Associative Joint Location for Human Pose Estimation in Videos
• Hierarchical Kinematic Human Mesh Recovery
• Learning Local Recurrent Models for Human Mesh Recovery