Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

TL;DR

This paper presents a weakly-supervised transfer learning approach for 3D human pose estimation in natural settings, combining 2D and 3D labels within an end-to-end deep network with geometric constraints.

Contribution

It introduces a unified, end-to-end deep network that jointly learns 2D pose and 3D depth estimation using mixed labels and geometric regularization, improving in-the-wild 3D pose estimation.

Findings

Achieves competitive results on 2D and 3D benchmarks.

Effectively transfers 3D pose knowledge from lab to wild images.

Utilizes geometric constraints to improve 3D predictions.

Abstract

In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learnt through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.