3D Human Pose Estimation in the Wild by Adversarial Learning

TL;DR

This paper introduces an adversarial learning framework with a novel geometric descriptor to improve 3D human pose estimation in wild images, effectively transferring knowledge from annotated datasets to in-the-wild images.

Contribution

It proposes a multi-source discriminator using geometric descriptors to enforce anthropometric validity in 3D pose predictions from in-the-wild images.

Findings

Significant performance improvement over previous methods.

Effective transfer of 3D pose structure knowledge.

Robustness in wild image scenarios.

Abstract

Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations. Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild. We also observe that a carefully designed information source for the discriminator is essential to boost the performance. Thus, we design a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator. The efficacy of our adversarial learning framework with the new geometric descriptor has been demonstrated through extensive experiments on widely used public benchmarks. Our approach significantly improves the performance compared with previous state-of-the-art approaches.