Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
This work addresses human pose estimation for computer vision applications, presenting an incremental improvement by integrating geometric constraints via adversarial learning.
The paper tackles the problem of deviated and biologically implausible human pose predictions in monocular images due to occlusions and overlapping, by proposing a structure-aware convolutional network that incorporates priors about human body structure through adversarial training, resulting in improved pose estimation.
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.