Unsupervised Remote Sensing Super-Resolution via Migration Image Prior

TL;DR

This paper introduces an unsupervised super-resolution method for satellite images that does not require low/high resolution pairs, using a generative adversarial network and migration image prior to enhance spatial resolution.

Contribution

The paper presents a novel unsupervised framework called MIP that improves satellite image super-resolution without needing paired training data, addressing a key practical limitation.

Findings

MIP outperforms state-of-the-art methods quantitatively.

MIP produces qualitatively sharper and more detailed images.

The method is validated on the Draper dataset with significant improvements.

Abstract

Recently, satellites with high temporal resolution have fostered wide attention in various practical applications. Due to limitations of bandwidth and hardware cost, however, the spatial resolution of such satellites is considerably low, largely limiting their potentials in scenarios that require spatially explicit information. To improve image resolution, numerous approaches based on training low-high resolution pairs have been proposed to address the super-resolution (SR) task. Despite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use. In this paper, we proposed a new unsupervised learning framework, called "MIP", which achieves SR tasks without low/high resolution image pairs. First, random noise maps are fed into a designed generative adversarial network (GAN) for reconstruction. Then, the proposed method converts the reference image to latent space as the migration image prior. Finally, we update the input noise via an implicit method, and further transfer the texture and structured information from the reference image. Extensive experimental results on the Draper dataset show that MIP achieves significant improvements over state-of-the-art methods both quantitatively and qualitatively. The proposed MIP is open-sourced at http://github.com/jiaming-wang/MIP.