SAR-to-EO Image Translation with Multi-Conditional Adversarial Networks

TL;DR

This paper introduces a multi-conditional adversarial network approach for SAR-to-EO image translation, leveraging multiple modalities like Google Maps and IR to enhance image quality and edge preservation, outperforming previous single-modality methods.

Contribution

It is the first to incorporate multiple complementary modalities into adversarial networks for SAR-to-EO image translation, significantly improving results.

Findings

Enhanced edge preservation in translated images.

Improved translation accuracy with additional modalities.

Effective across diverse datasets like SEN12MS, DFC2020, and SpaceNet6.

Abstract

This paper explores the use of multi-conditional adversarial networks for SAR-to-EO image translation. Previous methods condition adversarial networks only on the input SAR. We show that incorporating multiple complementary modalities such as Google maps and IR can further improve SAR-to-EO image translation especially on preserving sharp edges of manmade objects. We demonstrate effectiveness of our approach on a diverse set of datasets including SEN12MS, DFC2020, and SpaceNet6. Our experimental results suggest that additional information provided by complementary modalities improves the performance of SAR-to-EO image translation compared to the models trained on paired SAR and EO data only. To best of our knowledge, our approach is the first to leverage multiple modalities for improving SAR-to-EO image translation performance.