Learning Latent Representations of 3D Human Pose with Deep Neural Networks

Isinsu Katircioglu (1) , Bugra Tekin (1) , Mathieu Salzmann (1) , Vincent Lepetit (2) , Pascal Fua (1)

1 EPFL - Ecole Polytechnique Fédérale de Lausanne
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convo-lutional Neural Network to directly regress from an image to a 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 or 2D joint location heatmaps that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and accounts for joint dependencies. We further propose an efficient Long Short-Term Memory (LSTM) network to enforce temporal consistency on 3D pose predictions. We demonstrate that our approach achieves state-of-the-art performance both in terms of structure preservation and prediction accuracy on standard 3D human pose estimation benchmarks.

Domaines: Intelligence artificielle [cs.AI]

Isinsu Katircioglu, Bugra Tekin, Mathieu Salzmann, Vincent Lepetit, Pascal Fua. Learning Latent Representations of 3D Human Pose with Deep Neural Networks. International Journal of Computer Vision, 2018, 126 (12), pp.1326-1341. ⟨10.1007/s11263-018-1066-6⟩. ⟨hal-02509358⟩