Single image deraining (SID) is an important and challenging topic in emerging vision applications . Most of emerged deraining methods are supervised relying on the ground truth (i.e., paired images) in recent years . In practice it is rather common to have no un-paired images in real deraining task . In such cases how to remove 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 unsupervisory SID task using unpaired data and propose a novel net called Attention-guided Deraining by Constrained CycleGAN . 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 Rain 200A contains more obvious and diverse shapes and directions. As a result, existing supervised methods trained on Rain200B can perform much better for processing real rainy images . As well as existing methods, we show that our net is superior to existing networks, and is also very competitive to other related supervised networks. Extensive experiments on synthesis and real datasets

Links: PDF - Abstract

Code :


Keywords : deraining - rain - existing - images - task -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)