Monocular 3D Human Pose Estimation by Predicting Depth on Joints

Abstract

This paper aims at estimating full-body 3D human poses from monocular images of which the biggest challenge is the inherent ambiguity introduced by lifting the 2D pose into 3D space. We propose a novel framework focusing on reducing this ambiguity by predicting the depth of human joints based on 2D human joint locations and body part images. Our approach is… (More)
DOI: 10.1109/ICCV.2017.373

Topics

10 Figures and Tables