Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization

by   Yu Chen, et al.

Landmark/pose estimation in single monocular images have received much effort in computer vision due to its important applications. It remains a challenging task when input images severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, 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. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D single human pose estimation, 2D facial landmark estimation and 3D single human pose estimation. The proposed approach significantly outperforms the state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs.


page 2

page 3

page 9

page 10

page 11


AMIL: Adversarial Multi Instance Learning for Human Pose Estimation

Human pose estimation has an important impact on a wide range of applica...

OriNet: A Fully Convolutional Network for 3D Human Pose Estimation

In this paper, we propose a fully convolutional network for 3D human pos...

Self Adversarial Training for Human Pose Estimation

This paper presents a deep learning based approach to the problem of hum...

3D Human Pose Estimation in the Wild by Adversarial Learning

Recently, remarkable advances have been achieved in 3D human pose estima...

A Synchronized Reprojection-based Model for 3D Human Pose Estimation

3D human pose estimation is still a challenging problem despite the larg...

ContraNeRF: 3D-Aware Generative Model via Contrastive Learning with Unsupervised Implicit Pose Embedding

Although 3D-aware GANs based on neural radiance fields have achieved com...

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

Many classical Computer Vision problems, such as essential matrix comput...

Please sign up or login with your details

Forgot password? Click here to reset