# Creating High Resolution Images with a Latent Adversarial Generator

arXiv: https://arxiv.org/abs/2003.02365 · HTML: https://mlsanity.com/paper/2003.02365/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [High Perceptual Quality Image Denoising with a Posterior Sampling CGAN](https://mlsanity.com/paper/2103.04192/) (2021)
- [Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey](https://mlsanity.com/paper/2111.13282/) (2021)
- [Image-to-Image Translation with Low Resolution Conditioning](https://mlsanity.com/paper/2107.11262/) (2021)
- [Generative Adversarial Models for Extreme Geospatial Downscaling](https://mlsanity.com/paper/2402.14049/) (2024)
- [A Generative Model for Hallucinating Diverse Versions of Super Resolution Images](https://mlsanity.com/paper/2102.06624/) (2021)
- [Domain Agnostic Image-to-image Translation using Low-Resolution Conditioning](https://mlsanity.com/paper/2305.05023/) (2023)

## Abstract (arXiv)

Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say, instead of generating an arbitrary image as a sample from the manifold of natural images, we propose to sample images from a particular "subspace" of natural images, directed by a low-resolution image from the same subspace. The problem we address, while close to the formulation of the single-image super-resolution problem, is in fact rather different. Single image super-resolution is the task of predicting the image closest to the ground truth from a relatively low resolution image. We propose to produce samples of high resolution images given extremely small inputs with a new method called Latent Adversarial Generator (LAG). In our generative sampling framework, we only use the input (possibly of very low-resolution) to direct what class of samples the network should produce. As such, the output of our algorithm is not a unique image that relates to the input, but rather a possible se} of related images sampled from the manifold of natural images. Our method learns exclusively in the latent space of the adversary using perceptual loss -- it does not have a pixel loss.