University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling

Trumble, Matthew, Gilbert, Andrew, Hilton, Adrian and Collomosse, John (2018) Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling In: ECCV 2018: European Conference on Computer Vision, 08-14 Sep 2018, Munich, Germany.

[img]
Preview
Text
Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling.pdf - Accepted version Manuscript

Download (5MB) | Preview

Abstract

We present a method for simultaneously estimating 3D hu- man pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a latent representation that encodes skeletal joint positions, and at the same time learns a deep representation of volumetric body shape. We harness the latter to up-scale input volumetric data by a factor of 4X, whilst recovering a 3D estimate of joint positions with equal or greater accuracy than the state of the art. Inference runs in real-time (25 fps) and has the potential for passive human behaviour monitoring where there is a requirement for high fidelity estimation of human body shape and pose.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Arts and Social Sciences > Department of Music and Media
Authors :
NameEmailORCID
Trumble, Matthewmatthew.trumble@surrey.ac.uk
Gilbert, AndrewA.Gilbert@surrey.ac.uk
Hilton, AdrianA.Hilton@surrey.ac.uk
Collomosse, JohnJ.Collomosse@surrey.ac.uk
Date : 14 September 2018
Funders : Engineering and Physical Sciences Research Council (EPSRC)
Grant Title : The TotalCapture project
Copyright Disclaimer : © 2018 the authors
Uncontrolled Keywords : Deep Learning; Pose Estimation; Multiple Viewpoint Video
Related URLs :
Depositing User : Clive Harris
Date Deposited : 25 Jul 2018 13:20
Last Modified : 05 Mar 2019 10:13
URI: http://epubs.surrey.ac.uk/id/eprint/848781

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800