Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation

Abstract

For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. Under these circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of joint inter-connectivity. To address the problem by incorporating priors about the structure of human bodies, we propose a novel structure-aware convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator (G) generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors.

arXiv commentFixed typos. 14 pages. Demonstration videos are http://v.qq.com/x/page/c039862eira.html, http://v.qq.com/x/page/f0398zcvkl5.html, http://v.qq.com/x/page/w0398ei9m1r.html

References in corpus (12)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Residual Learning for Image Recognition
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Generative Adversarial Text to Image Synthesis
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Techniques for Training GANs
• Human pose estimation via Convolutional Part Heatmap Regression
• Stacked Hourglass Networks for Human Pose Estimation
• Deep multi-scale video prediction beyond mean square error
• Convolutional Pose Machines
• DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
• Human Pose Estimation using Deep Consensus Voting

Cited by in corpus (24)

• FCOS: Fully Convolutional One-Stage Object Detection
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Numerical Coordinate Regression with Convolutional Neural Networks
• Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio
• Analyzing Human-Human Interactions: A Survey
• Human Pose Estimation with Spatial Contextual Information
• A Survey on Deep Learning Methods for Robot Vision
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• Improved training of binary networks for human pose estimation and image recognition
• Self Adversarial Training for Human Pose Estimation
• FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
• SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Integral Human Pose Regression
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• In-bed Pressure-based Pose Estimation using Image Space Representation Learning
• Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
• CU-Net: Coupled U-Nets
• RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation
• Learning to Refine Human Pose Estimation
• 3D Human Pose Estimation with 2D Marginal Heatmaps
• Geometry-Aware Face Completion and Editing
• View Invariant 3D Human Pose Estimation
• Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation