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

I. Katircioglu, B. Tekin*, M. Salzmann, Vincent Lepetit, Pascal Fua

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional 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 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
Original languageEnglish
Pages (from-to)1326-1341
JournalInternational Journal of Computer Vision
Publication statusPublished - 2018
Externally publishedYes


Dive into the research topics of 'Learning Latent Representations of 3D Human Pose with Deep Neural Networks'. Together they form a unique fingerprint.

Cite this