Restoration of Historical Illustrations using Generative Adversarial Networks

Generative Adversarial Network (GANs) is widely implemented not just for image generation but also text, audio, video processing, and more. To add on, methods of image restoration and enhancement such as semantic inpainting, outpainting, filtering, and denoising are achievable by GANs. This paper reviews the theoretical basis of GANs in image generation, also known as image synthesis, and possibilities of successful restoration of historical illustrations such as buildings, landmarks, and cultural heritage that have been lost or demolished. By training GANs on a relevant dataset of images, it can learn characteristics and features of the dataset to generate desired results based on raw image as input. Theoretical knowledge about GANs and relevancy of study is elaborated. For methodology, random sampling and stratified sampling are applied for data collection with justifications together with limitations. The proposed system, HistoGAN, restores damaged or incomplete images through image synthesis after being trained with large datasets. Performance of implementation is analyzed and evaluated to identify space of improvement to uplift performance. HistoGAN has the potential to be applicable in other fields such as historical research, architecture discovery, and education.