Unsupervised Network for Single Image Raindrop Removal

TL;DR

This paper introduces an unsupervised deep neural network that effectively removes raindrops from images by separating layers and iteratively refining results, eliminating the need for paired training data.

Contribution

It proposes a novel unsupervised cycle network architecture with feedback mechanism for layer separation and raindrop removal in images, reducing reliance on paired datasets.

Findings

Outperforms existing methods on benchmark datasets

Achieves higher quantitative metrics and visual quality

Demonstrates effective layer separation and iterative refinement

Abstract

Image quality degradation caused by raindrops is one of the most important but challenging problems that reduce the performance of vision systems. Most existing raindrop removal algorithms are based on a supervised learning method using pairwise images, which are hard to obtain in real-world applications. This study proposes a deep neural network for raindrop removal based on unsupervised learning, which only requires two unpaired image sets with and without raindrops. Our proposed model performs layer separation based on cycle network architecture, which aims to separate a rainy image into a raindrop layer, a transparency mask, and a clean background layer. The clean background layer is the target raindrop removal result, while the transparency mask indicates the spatial locations of the raindrops. In addition, the proposed model applies a feedback mechanism to benefit layer separation by refining low-level representation with high-level information. i.e., the output of the previous iteration is used as input for the next iteration, together with the input image with raindrops. As a result, raindrops could be gradually removed through this feedback manner. Extensive experiments on raindrop benchmark datasets demonstrate the effectiveness of the proposed method on quantitative metrics and visual quality.