Augmenting Cats and Dogs: Procedural Texturing for Generalized Pet Tracking

Dominik Borer, Nihat Isik, Jakob Buhmann, Martin Guay

Abstract

Cats and dogs being humanity’s favoured domestic pets occupy a large portion of the internet and of our digital lives. However, augmented reality technology — while becoming pervasive for humans — has so far mostly left out our beloved pets out of the picture due to limited enabling technology. While there are well-established learning frameworks for human pose estimation, they mostly rely on large datasets of hand-labelled images, such as Microsoft’s COCO (Lin et al., 2014) or facebook’s dense pose (Güler et al., 2018). Labelling large datasets is time-consuming and expensive, and manually labelling 3D information is difficult to do consistently. Our solution to these problem is to synthesize highly varied datasets of animals, together with their corresponding 3D information such as pose. To generalize to various animals and breeds, as well as to the real-world domain, we leverage domain randomization over traditional dimensions (background, color variations and image transforms), but as well as with novel procedural appearance variations in breed, age and species. We evaluate the validity of our approach on various benchmarks, and produced several 3D graphical augmentations of real world cats and dogs using our fully synthetic approach.

Download


Paper Citation


in Harvard Style

Borer D., Isik N., Buhmann J. and Guay M. (2021). Augmenting Cats and Dogs: Procedural Texturing for Generalized Pet Tracking.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 978-989-758-488-6, pages 122-132. DOI: 10.5220/0010333701220132


in Bibtex Style

@conference{grapp21,
author={Dominik Borer and Nihat Isik and Jakob Buhmann and Martin Guay},
title={Augmenting Cats and Dogs: Procedural Texturing for Generalized Pet Tracking},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2021},
pages={122-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010333701220132},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - Augmenting Cats and Dogs: Procedural Texturing for Generalized Pet Tracking
SN - 978-989-758-488-6
AU - Borer D.
AU - Isik N.
AU - Buhmann J.
AU - Guay M.
PY - 2021
SP - 122
EP - 132
DO - 10.5220/0010333701220132