# Deep Snow: Synthesizing Remote Sensing Imagery with Generative Adversarial Nets

arXiv: https://arxiv.org/abs/2005.08892 · HTML: https://mlsanity.com/paper/2005.08892/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 5 of 5)

- [Distracting Downpour: Adversarial Weather Attacks for Motion Estimation](https://mlsanity.com/paper/2305.06716/) (2023)
- [Attacking Motion Estimation with Adversarial Snow](https://mlsanity.com/paper/2210.11242/) (2022)
- [Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images](https://mlsanity.com/paper/2301.07743/) (2023)
- [Mask Conditional Synthetic Satellite Imagery](https://mlsanity.com/paper/2302.04305/) (2023)
- [SpecSwin3D: Generating Hyperspectral Imagery from Multispectral Data via Transformer Networks](https://mlsanity.com/paper/2509.06122/) (2025)

## Abstract (arXiv)

In this work we demonstrate that generative adversarial networks (GANs) can be used to generate realistic pervasive changes in remote sensing imagery, even in an unpaired training setting. We investigate some transformation quality metrics based on deep embedding of the generated and real images which enable visualization and understanding of the training dynamics of the GAN, and may provide a useful measure in terms of quantifying how distinguishable the generated images are from real images. We also identify some artifacts introduced by the GAN in the generated images, which are likely to contribute to the differences seen between the real and generated samples in the deep embedding feature space even in cases where the real and generated samples appear perceptually similar.