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.

@inproceedings{yu2019texture,
  author = {Yu, Ning and Barnes, Connelly and Shechtman, Eli and Amirghodsi, Sohrab and Luk\'{a}\v{c}, Michal},
  title = {Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019}
}