Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video

TL;DR

This paper presents a novel method for 3D human pose estimation from monocular video, combining sparsity priors, temporal smoothness, and deep learning to improve accuracy in both known and unknown joint location scenarios.

Contribution

It introduces a unified framework that integrates a sparsity-driven geometric prior with deep uncertainty prediction and EM optimization for improved 3D pose estimation from monocular video.

Findings

Achieves higher accuracy than state-of-the-art methods on Human3.6M.

Outperforms existing 2D pose estimators on PennAction.

Effectively handles unknown joint locations using latent variables.

Abstract

This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are unknown. In the former case, a novel approach is introduced that integrates a sparsity-driven 3D geometric prior and temporal smoothness. In the latter case, the former case is extended by treating the image locations of the joints as latent variables. A deep fully convolutional network is trained to predict the uncertainty maps of the 2D joint locations. The 3D pose estimates are realized via an Expectation-Maximization algorithm over the entire sequence, where it is shown that the 2D joint location uncertainties can be conveniently marginalized out during inference. Empirical evaluation on the Human3.6M dataset shows that the proposed approaches achieve greater 3D pose estimation accuracy over state-of-the-art baselines. Further, the proposed approach outperforms a publicly available 2D pose estimation baseline on the challenging PennAction dataset.