1st Place Solution to MultiEarth 2023 Challenge on Multimodal SAR-to-EO Image Translation

TL;DR

This paper presents the winning solution for the MultiEarth 2023 challenge, utilizing a novel Clean Collector Algorithm with advanced image translation and enhancement techniques to convert SAR data into high-quality EO images.

Contribution

The paper introduces the Clean Collector Algorithm (CCA) for effective SAR data utilization and combines pix2pixHD and Restormer models for superior SAR-to-EO image translation and enhancement.

Findings

Achieved top MAE score of 0.07313 in the challenge

Demonstrated effectiveness of CCA in handling cloud obstructions

Secured 1st place in the MultiEarth 2023 leaderboard

Abstract

The Multimodal Learning for Earth and Environment Workshop (MultiEarth 2023) aims to harness the substantial amount of remote sensing data gathered over extensive periods for the monitoring and analysis of Earth's ecosystems'health. The subtask, Multimodal SAR-to-EO Image Translation, involves the use of robust SAR data, even under adverse weather and lighting conditions, transforming it into high-quality, clear, and visually appealing EO data. In the context of the SAR2EO task, the presence of clouds or obstructions in EO data can potentially pose a challenge. To address this issue, we propose the Clean Collector Algorithm (CCA), designed to take full advantage of this cloudless SAR data and eliminate factors that may hinder the data learning process. Subsequently, we applied pix2pixHD for the SAR-to-EO translation and Restormer for image enhancement. In the final evaluation, the team 'CDRL' achieved an MAE of 0.07313, securing the top rank on the leaderboard.