Unsupervised Network for Single Image Raindrop Removal
This addresses the challenge of raindrop removal for vision systems, offering an unsupervised approach that avoids the need for hard-to-obtain paired images, though it appears incremental as it builds on existing cycle network architectures.
The study tackled the problem of removing raindrops from images to improve vision system performance by proposing an unsupervised deep neural network that separates rainy images into layers, achieving effectiveness on benchmark datasets with quantitative metrics and visual quality.
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.