Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling

Matthew Trumble, Andrew Gilbert, Adrian Hilton, John Collomosse; The European Conference on Computer Vision (ECCV), 2018, pp. 784-800

Abstract


We present a method for simultaneously estimating 3D human 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 for 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 potential for passive human behavior monitoring where there is a requirement for high fidelity estimation of human body shape and pose.

Related Material


[pdf]
[bibtex]
@InProceedings{Trumble_2018_ECCV,
author = {Trumble, Matthew and Gilbert, Andrew and Hilton, Adrian and Collomosse, John},
title = {Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling},
booktitle = {The European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}