Absolute Human Pose Estimation with Depth Prediction Network
Computer Vision and Pattern Recognition
2019-04-15 v1
Abstract
The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.
Cite
@article{arxiv.1904.05947,
title = {Absolute Human Pose Estimation with Depth Prediction Network},
author = {Márton Véges and András Lőrincz},
journal= {arXiv preprint arXiv:1904.05947},
year = {2019}
}
Comments
Accepted to IJCNN 2019