# LocoGAN -- Locally Convolutional GAN

arXiv: https://arxiv.org/abs/2002.07897 · HTML: https://mlsanity.com/paper/2002.07897/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://mlsanity.com/paper/2207.09814/) (2022)
- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN](https://mlsanity.com/paper/2301.11631/) (2023)
- [Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis](https://mlsanity.com/paper/2309.02340/) (2023)

## Abstract (arXiv)

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).