A Generative Adversarial Approach with Residual Learning for Dust and Scratches Artifacts Removal

TL;DR

This paper introduces a GAN-based method with residual learning to effectively remove dust and scratches from film scans, outperforming existing techniques and generalizing well across diverse images.

Contribution

The proposed approach combines GANs with residual learning for improved dust and scratch artifact removal in film scans, demonstrating superior performance over prior methods.

Findings

Outperforms state-of-the-art methods in artifact removal

Generalizes well across different types of images

Speeds up training and enhances denoising performance

Abstract

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to operate in a professional manner. One particularly challenging task for old photo retouching remains the removal of dust and scratches artifacts. Traditionally, this task has been completed manually with special image enhancement software and represents a tedious task that requires special know-how of photo editing applications. However, recent research utilizing Generative Adversarial Networks (GANs) has been proven to obtain good results in various automated image enhancement tasks compared to traditional methods. This motivated us to explore the use of GANs in the context of film photo editing. In this paper, we present a GAN based method that is able to remove dust and scratches errors from film scans. Specifically, residual learning is utilized to speed up the training process, as well as boost the denoising performance. An extensive evaluation of our model on a community provided dataset shows that it generalizes remarkably well, not being dependent on any particular type of image. Finally, we significantly outperform the state-of-the-art methods and software applications, providing superior results.