# A Novel Framework for Remote Sensing Image Synthesis with Optimal Transport

## TL;DR

This paper introduces a new GAN-based method for generating realistic remote sensing images using attention modules and optimal transport.

## Contribution

The novel integration of two attention modules and optimal transport in a GAN framework for remote sensing image synthesis.

## Key findings

- The attention modules effectively handle intraclass and interclass variance in remote sensing images.
- Optimal transport improves the visual quality of synthesized images by approximating human perceptual loss.
- Experimental results show significant enhancement in the quality of generated remote sensing images.

## Abstract

We propose a Generative Adversarial Network (GAN)-based method for image synthesis from remote sensing data. Remote sensing images (RSIs) are characterized by large intraclass variance and small interclass variance, which pose significant challenges for image synthesis. To address these issues, we design and incorporate two distinct attention modules into our GAN framework. The first attention module is designed to enhance similarity measurements within label groups, effectively handling the large intraclass variance by reinforcing consistency within the same class. The second module addresses the small interclass variance by promoting diversity between adjacent label groups, ensuring that different classes are distinguishable in the generated images. These attention mechanisms play a critical role in generating more realistic and visually coherent images. Our GAN-based framework consists of an advanced image encoder and a generator, which are both enhanced by these attention modules. Furthermore, we integrate optimal transport (OT) to approximate human perceptual loss, further improving the visual quality of the synthesized images. Experimental results demonstrate the effectiveness of our approach, highlighting its advantages in the remote sensing field by significantly enhancing the quality of generated RSIs.