Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video

TL;DR

This paper introduces a method that leverages temporal joint depth information in videos to enhance the accuracy of 3D human pose estimation, addressing depth ambiguity issues present in 2D pose predictions.

Contribution

It proposes a novel approach that refines 3D human poses by incorporating temporal joint depth information, improving accuracy over existing methods.

Findings

Reduced depth ambiguity in 3D pose estimation

Improved accuracy in 3D human pose predictions

Effective use of temporal information in videos

Abstract

The effectiveness of the approaches to predict 3D poses from 2D poses estimated in each frame of a video has been demonstrated for 3D human pose estimation. However, 2D poses without appearance information of persons have much ambiguity with respect to the joint depths. In this paper, we propose to estimate a 3D pose in each frame of a video and refine it considering temporal information. The proposed approach reduces the ambiguity of the joint depths and improves the 3D pose estimation accuracy.