Rain structure transfer using an exemplar rain image for synthetic rain image generation
This work addresses the need for high-quality synthetic rain images for applications like rain removal, though it is incremental as it builds on existing patch-based transfer methods.
The authors tackled the problem of generating realistic synthetic rain images by transferring rain structures from an exemplar rain image to a target image, resulting in the creation of images with similar rain structures as shown in their experiments.
This letter proposes a simple method of transferring rain structures of a given exemplar rain image into a target image. Given the exemplar rain image and its corresponding masked rain image, rain patches including rain structures are extracted randomly, and then residual rain patches are obtained by subtracting those rain patches from their mean patches. Next, residual rain patches are selected randomly, and then added to the given target image along a raster scanning direction. To decrease boundary artifacts around the added patches on the target image, minimum error boundary cuts are found using dynamic programming, and then blending is conducted between overlapping patches. Our experiment shows that the proposed method can generate realistic rain images that have similar rain structures in the exemplar images. Moreover, it is expected that the proposed method can be used for rain removal. More specifically, natural images and synthetic rain images generated via the proposed method can be used to learn classifiers, for example, deep neural networks, in a supervised manner.