# Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning

arXiv: https://arxiv.org/abs/1711.10312 · HTML: https://mlsanity.com/paper/1711.10312/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2017.

## Built on by (most cited first, 4 of 4)

- [Semantically Accurate Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/2205.08659/) (2022)
- [Single Image Super-Resolution Methods: A Survey](https://mlsanity.com/paper/2202.11763/) (2022)
- [Deep priors for satellite image restoration with accurate uncertainties](https://mlsanity.com/paper/2412.04130/) (2024)
- [Improved detection of small objects in road network sequences](https://mlsanity.com/paper/2105.08416/) (2021)

## Abstract (arXiv)

Recent advances in Generative Adversarial Learning allow for new modalities of image super-resolution by learning low to high resolution mappings. In this paper we present our work using Generative Adversarial Networks (GANs) with applications to overhead and satellite imagery. We have experimented with several state-of-the-art architectures. We propose a GAN-based architecture using densely connected convolutional neural networks (DenseNets) to be able to super-resolve overhead imagery with a factor of up to 8x. We have also investigated resolution limits of these networks. We report results on several publicly available datasets, including SpaceNet data and IARPA Multi-View Stereo Challenge, and compare performance with other state-of-the-art architectures.