Structured Prediction of 3D Human Pose with Deep Neural Networks

Bugra Tekin, Isinsu Katircioglu, Mathieu Salzmann, Vincent Lepetit and Pascal Fua

Abstract

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and account for joint dependencies. We demonstrate that our approach outperforms state-of-the-art ones both in terms of structure preservation and prediction accuracy.

Session

Recognition

Files

Extended Abstract (PDF, 302K)
Paper (PDF, 800K)

DOI

10.5244/C.30.130
https://dx.doi.org/10.5244/C.30.130

Citation

Bibtex

        @inproceedings{BMVC2016_130,
        	title={Structured Prediction of 3D Human Pose with Deep Neural Networks},
        	author={Bugra Tekin, Isinsu Katircioglu, Mathieu Salzmann, Vincent Lepetit and Pascal Fua},
        	year={2016},
        	month={September},
        	pages={130.1-130.11},
        	articleno={130},
        	numpages={11},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.130},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.130}
        }