Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

TL;DR

This paper introduces an unsupervised adversarial learning method for 3D human pose estimation from 2D joint locations in a single image, eliminating the need for 3D datasets during training.

Contribution

It presents the first method to learn 3D human poses from 2D joints without relying on 3D datasets, using generative adversarial networks in an unsupervised manner.

Findings

Accurately predicts 3D poses without 3D training data.

Works effectively on Human3.6M and MPII datasets.

Demonstrates robustness in 3D pose estimation from 2D joints.

Abstract

The task of three-dimensional (3D) human pose estimation from a single image can be divided into two parts: (1) Two-dimensional (2D) human joint detection from the image and (2) estimating a 3D pose from the 2D joints. Herein, we focus on the second part, i.e., a 3D pose estimation from 2D joint locations. The problem with existing methods is that they require either (1) a 3D pose dataset or (2) 2D joint locations in consecutive frames taken from a video sequence. We aim to solve these problems. For the first time, we propose a method that learns a 3D human pose without any 3D datasets. Our method can predict a 3D pose from 2D joint locations in a single image. Our system is based on the generative adversarial networks, and the networks are trained in an unsupervised manner. Our primary idea is that, if the network can predict a 3D human pose correctly, the 3D pose that is projected onto a 2D plane should not collapse even if it is rotated perpendicularly. We evaluated the performance of our method using Human3.6M and the MPII dataset and showed that our network can predict a 3D pose well even if the 3D dataset is not available during training.