A Dual-Source Approach for 3D Pose Estimation From a Single Image
Hashim Yasin, Umar Iqbal, Bjorn Kruger, Andreas Weber, Juergen Gall
Abstract
One major challenge for 3D pose estimation from a single RGB image is the acquisition of sufficient training data. In particular, collecting large amounts of training data that contain unconstrained images and are annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of images with annotated 2D poses and the second source consists of accurate 3D motion capture data. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient and robust 3D pose retrieval. In our experiments, we show that our approach achieves state-of-the-art results and is even competitive when the skeleton structure of the two sources differ substantially.
BibTeX
@inproceedings{cvpr2016_adualsourceappro,
title = {A Dual-Source Approach for 3D Pose Estimation From a Single Image},
author = {Hashim Yasin and Umar Iqbal and Bjorn Kruger and Andreas Weber and Juergen Gall},
booktitle = {CVPR 2016},
year = {2016}
}