BriefGPT.xyz
Apr, 2017
对抗 PoseNet：一种结构感知的卷积网络，用于人体姿态估计
Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
HTML
PDF
Yu Chen, Chunhua Shen, Xiu-Sheng Wei, Lingqiao Liu, Jian Yang
TL;DR
本文使用结构感知卷积网络来隐式地将人体结构的先验信息纳入深度网络的训练，以便在单目图像中实现更好的人体姿态估计。
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 ma
→