User-controllable Multi-texture Synthesis with Generative Adversarial Networks

Aibek Alanov, Aibek Alanov, Aibek Alanov, Max Kochurov, Max Kochurov, Denis Volkhonskiy, Daniil Yashkov, Evgeny Burnaev, Dmitry Vetrov, Dmitry Vetrov

2020

Abstract

We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism. The user control ability allows to explicitly specify the texture which should be generated by the model. This property follows from using an encoder part which learns a latent representation for each texture from the dataset. To ensure a dataset coverage, we use an adversarial loss function that penalizes for incorrect reproductions of a given texture. In experiments, we show that our model can learn descriptive texture manifolds for large datasets and from raw data such as a collection of high-resolution photos. We show our unsupervised learning pipeline may help segmentation models. Moreover, we apply our method to produce 3D textures and show that it outperforms existing baselines.

Paper Citation

in Harvard Style

Alanov A., Kochurov M., Volkhonskiy D., Yashkov D., Burnaev E. and Vetrov D. (2020). User-controllable Multi-texture Synthesis with Generative Adversarial Networks. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 214-221. DOI: 10.5220/0008924502140221

in Bibtex Style

@conference{visapp20,
author={Aibek Alanov and Max Kochurov and Denis Volkhonskiy and Daniil Yashkov and Evgeny Burnaev and Dmitry Vetrov},
title={User-controllable Multi-texture Synthesis with Generative Adversarial Networks},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={214-221},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008924502140221},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - User-controllable Multi-texture Synthesis with Generative Adversarial Networks
SN - 978-989-758-402-2
AU - Alanov A.
AU - Kochurov M.
AU - Volkhonskiy D.
AU - Yashkov D.
AU - Burnaev E.
AU - Vetrov D.
PY - 2020
SP - 214
EP - 221
DO - 10.5220/0008924502140221
PB - SciTePress