Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Abstract
This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by-example controllability and (2) realistic and smooth interpolation among an arbitrary number of texture samples. To solve it we propose a neural network trained simultaneously on a reconstruction task and a generation task, which can project texture examples onto a latent space where they can be linearly interpolated and projected back onto the image domain, thus ensuring both intuitive control and realistic results. We show our method outperforms a number of baselines according to a comprehensive suite of metrics as well as a user study. We further show several applications based on our technique, which include texture brush, texture dissolve, and animal hybridization.
Cite
Text
Yu et al. "Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01244Markdown
[Yu et al. "Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/yu2019cvpr-texture/) doi:10.1109/CVPR.2019.01244BibTeX
@inproceedings{yu2019cvpr-texture,
title = {{Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture}},
author = {Yu, Ning and Barnes, Connelly and Shechtman, Eli and Amirghodsi, Sohrab and Lukac, Michal},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01244},
url = {https://mlanthology.org/cvpr/2019/yu2019cvpr-texture/}
}