Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

TL;DR

This paper introduces a geometry-aware representation learning method for 3D human pose estimation that leverages multi-view images without annotations, significantly reducing the need for labeled data and outperforming existing methods.

Contribution

It proposes a novel unsupervised approach to learn 3D geometry-aware representations from multi-view images, enhancing semi-supervised 3D pose estimation.

Findings

Outperforms fully-supervised methods with the same labeled data

Improves semi-supervised methods using as little as 1% labeled data

Effectively learns 3D geometry from unannotated multi-view images

Abstract

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1% of the labeled data.