2017
Monocular 3D Human Pose Estimation by Predicting Depth on Joints
ICCV 2017poster
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…