Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling
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.
Cite
Text
Trumble et al. "Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01249-6_48Markdown
[Trumble et al. "Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/trumble2018eccv-deep/) doi:10.1007/978-3-030-01249-6_48BibTeX
@inproceedings{trumble2018eccv-deep,
title = {{Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling}},
author = {Trumble, Matthew and Gilbert, Andrew and Hilton, Adrian and Collomosse, John},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01249-6_48},
url = {https://mlanthology.org/eccv/2018/trumble2018eccv-deep/}
}