Using Simulated Data to Generate Images of Climate Change

TL;DR

This paper investigates using simulated 3D environment images to enhance domain adaptation in GANs, specifically MUNIT, for generating climate change images to raise awareness, addressing data scarcity issues.

Contribution

It demonstrates that simulated data can improve GAN-based image generation for climate change visualization, reducing dependence on real data.

Findings

Simulated data enhances image quality in climate change visualization.

Using simulated images improves domain adaptation performance.

The approach aids in raising climate change awareness.

Abstract

Generative adversarial networks (GANs) used in domain adaptation tasks have the ability to generate images that are both realistic and personalized, transforming an input image while maintaining its identifiable characteristics. However, they often require a large quantity of training data to produce high-quality images in a robust way, which limits their usability in cases when access to data is limited. In our paper, we explore the potential of using images from a simulated 3D environment to improve a domain adaptation task carried out by the MUNIT architecture, aiming to use the resulting images to raise awareness of the potential future impacts of climate change.