Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang• 2017

Related benchmarks

TaskDatasetResultRank
Human Pose EstimationMPII (test)
Shoulder PCK96.5
314
Human Pose EstimationLSP (test)
Head Accuracy98.5
102
Facial Landmark Detection300W official (test)
AUC (0.08)53.64
32
Human Pose EstimationMPII pose 03/15/2018 (full)
Head Accuracy98.1
11
Showing 4 of 4 rows

Other info

Follow for update