Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer

TL;DR

This paper introduces an unsupervised domain adaptation method using adversarial learning to enhance low-resolution satellite images by leveraging high-resolution data, improving material and semantic label transfer.

Contribution

It presents a novel unsupervised approach for super-resolving satellite imagery by transferring knowledge from high-resolution data without requiring annotations.

Findings

Effective super-resolution of satellite images achieved

Improved material and semantic label transfer demonstrated

Method reduces reliance on extensive human annotations

Abstract

Urban material recognition in remote sensing imagery is a highly relevant, yet extremely challenging problem due to the difficulty of obtaining human annotations, especially on low resolution satellite images. To this end, we propose an unsupervised domain adaptation based approach using adversarial learning. We aim to harvest information from smaller quantities of high resolution data (source domain) and utilize the same to super-resolve low resolution imagery (target domain). This can potentially aid in semantic as well as material label transfer from a richly annotated source to a target domain.