3D Pose Estimation from a Single Monocular Image

Hashim Yasin, Umar Iqbal, Björn Krüger, Andreas Weber und Juergen Gall
Universität Bonn, Technical Report number CG-2015-1 arXiv:1509.06720v1, Sept. 2015
 

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 when both sources are from the same dataset, but it also achieves competitive results when the motion capture data is taken from a different dataset.

Bilder

Paper herunterladen

Paper herunterladen

Bibtex

@TECHREPORT{yasin2015,
       author = {Yasin, Hashim and Iqbal, Umar and Kr{\"u}ger, Bj{\"o}rn and Weber, Andreas and Gall, Juergen},
        title = {3D Pose Estimation from a Single Monocular Image},
       number = {CG-2015-1 arXiv:1509.06720v1},
         year = {2015},
        month = sep,
  institution = {Universit{\"a}t Bonn},
     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 when both sources
                 are from the same dataset, but it also achieves competitive results when the motion capture data is
                 taken from a different dataset.},
          url = {http://arxiv.org/pdf/1509.06720.pdf}
}