UnfairGAN: An Enhanced Generative Adversarial Network for Raindrop Removal from A Single Image

TL;DR

UnfairGAN is a novel GAN-based model that leverages high-level prior information like edges and rain estimation to effectively remove raindrops from single images, improving visibility in adverse weather conditions.

Contribution

This paper introduces UnfairGAN, an enhanced GAN architecture that incorporates prior high-level information for improved raindrop removal from images.

Findings

Outperforms state-of-the-art deraining methods in quantitative metrics

Demonstrates superior visual quality in raindrop removal

Introduces a large dataset for training rain removal models

Abstract

Image deraining is a new challenging problem in real-world applications, such as autonomous vehicles. In a bad weather condition of heavy rainfall, raindrops, mainly hitting glasses or windshields, can significantly reduce observation ability. Moreover, raindrops spreading over the glass can yield refraction's physical effect, which seriously impedes the sightline or undermine machine learning systems. In this paper, we propose an enhanced generative adversarial network to deal with the challenging problems of raindrops. UnfairGAN is an enhanced generative adversarial network that can utilize prior high-level information, such as edges and rain estimation, to boost deraining performance. To demonstrate UnfairGAN, we introduce a large dataset for training deep learning models of rain removal. The experimental results show that our proposed method is superior to other state-of-the-art approaches of deraining raindrops regarding quantitative metrics and visual quality.