Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People

TL;DR

This paper introduces a temporal smoothing method for 3D human pose estimation that improves accuracy during occlusions by generating smooth trajectories, and presents a new synthetic dataset for evaluation.

Contribution

It proposes an energy minimization approach for temporal smoothing that outperforms interpolation methods and introduces the MuCo-Temp dataset for benchmarking.

Findings

Outperforms other interpolation methods in occlusion scenarios

Achieves state-of-the-art results in 3D pose estimation during occlusions

Provides a new synthetic dataset for temporal pose estimation evaluation

Abstract

In multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person. While temporal methods can still predict a reasonable estimation for a temporarily disappeared pose using past and future frames, they exhibit large errors nevertheless. We present an energy minimization approach to generate smooth, valid trajectories in time, bridging gaps in visibility. We show that it is better than other interpolation based approaches and achieves state of the art results. In addition, we present the synthetic MuCo-Temp dataset, a temporal extension of the MuCo-3DHP dataset. Our code is made publicly available.