Refined single image rain removal method based on generative adversarial network

Abstract

The invention relates to a refined single image rain removing method based on a generative adversarial network. Inputting the rain image into a rain streak estimation network; obtaining an estimated rain streak graph; connecting with an input image to form a multi-channel image; the rain-free image generated by the generation model is input into the discriminator for judgment, the generator is optimized according to a judgment result, a generator network with high rain removal capability is finally obtained, the output of the generation model serves as the input of the image refinement network, the image is further processed, and a final rain-free image is obtained. The algorithm provided by the invention is an end-to-end algorithm, and any additional preprocessing and post-processing arenot needed. Compared with other work of using a generative adversarial network to carry out a single image area, two auxiliary networks are provided, and the image rain removal effect can be further improved while the calculated amount is not significantly increased.

Description

technical field [0001] The invention belongs to the field of multimedia image processing, and relates to computer vision and deep learning technology, in particular to a method for removing rain from a single image based on a generative confrontation network. [0002] technical background [0003] Rain is the most common severe weather, and images obtained in rainy days often have poor visual effects. At the same time, many computer vision algorithms usually input clean images by default, so images with rain often have a bad impact on these algorithms and reduce their performance. The method of removing rain from a single image is to use the existing prior information to process the input image to obtain a clean image without rain. [0004] Deraining algorithms are mainly divided into video deraining and image deraining. Video and image deraining algorithms have been developed relatively maturely. These models can use the time information in the video to accurately locate r...

AI Technical Summary

Problems solved by technology

However, although they have achieved good results on some data sets, due to the large changes in the density and direction of raindrops in different images, they cannot be practically applied to specific scenes.

Images