LocoGAN -- Locally Convolutional GAN
This addresses the need for flexible image generation in domains like panoramic photography or wallpaper design, though it appears incremental as it builds on existing GAN architectures.
The paper tackled the problem of generating images of arbitrary dimensions and periodic patterns by introducing LocoGAN, a fully convolutional GAN with a locally processed latent space, resulting in the ability to produce images like LSUN bedroom data and cylindrical panoramic images.
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).