LocoGAN -- Locally Convolutional GAN
Image and Video Processing
2023-11-03 v2 Computer Vision and Pattern Recognition
Machine Learning
Abstract
In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions. The learning is local, i.e. we process not the whole noise-like image, but the sub-images of a fixed size. As a consequence LocoGAN can produce images of arbitrary dimensions e.g. LSUN bedroom data set. Another advantage of our approach comes from the fact that we use the position channels, which allows the generation of fully periodic (e.g. cylindrical panoramic images) or almost periodic ,,infinitely long" images (e.g. wall-papers).
Keywords
Cite
@article{arxiv.2002.07897,
title = {LocoGAN -- Locally Convolutional GAN},
author = {Łukasz Struski and Szymon Knop and Jacek Tabor and Wiktor Daniec and Przemysław Spurek},
journal= {arXiv preprint arXiv:2002.07897},
year = {2023}
}