DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking

TL;DR

This paper introduces DerainCycleGAN, an unsupervised learning framework for single image deraining that leverages a novel attention-guided rain streak extractor and a new dataset, improving real-world rain removal performance.

Contribution

The paper proposes a novel unsupervised deraining network with an attention-guided rain streak extractor and introduces a new diverse rain image dataset, Rain200A.

Findings

Outperforms existing unsupervised deraining methods.

Achieves competitive results with supervised networks.

Provides a new dataset with diverse rain streaks.

Abstract

Single image deraining (SID) is an important and challenging topic in emerging vision applications, and most of emerged deraining methods are supervised relying on the ground truth (i.e., paired images) in recent years. However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results. In this paper, we explore the unsupervised SID task using unpaired data and propose a novel net called Attention-guided Deraining by Constrained CycleGAN (or shortly, DerainCycleGAN), which can fully utilize the constrained transfer learning abilitiy and circulatory structure of CycleGAN. Specifically, we design an unsu-pervised attention guided rain streak extractor (U-ARSE) that utilizes a memory to extract the rain streak masks with two constrained cycle-consistency branches jointly by paying attention to both the rainy and rain-free image domains. As a by-product, we also contribute a new paired rain image dataset called Rain200A, which is constructed by our network automatically. Compared with existing synthesis datasets, the rainy streaks in Rain200A contains more obvious and diverse shapes and directions. As a result, existing supervised methods trained on Rain200A can perform much better for processing real rainy images. Extensive experiments on synthesis and real datasets show that our net is superior to existing unsupervised deraining networks, and is also very competitive to other related supervised networks.