Single image rain removal method based on multi-scale fusion generative adversarial network

Abstract

The invention provides a single image rain removal method based on a multi-scale fusion generative adversarial network. The method comprises the following steps of firstly, detecting a rain image through image saliency to obtain a saliency map, fusing the saliency map with a rain image Concat, and accurately recognizing a raindrop area to be restored, then, using multi-scale fusion to generate anadversarial network for rain removal, conducting multi-scale fusion on l12, l14 and l16 layers of networks in a generator network, enhancing the quality of a generated rain removal image, enabling thediscriminator network to adopt combination of global discrimination and local discrimination, and conducting training to obtain a final network model, and inputting the test set into the trained model to obtain a rain removed image, and evaluating the generated image according to the SSIM and PSNR indexes. The image generated by the image rain removal method provided by the invention is better invisual effect, the removed raindrop area is more authentic and coherent, and each evaluation index is improved.

Description

technical field [0001] The invention relates to the technical field of image restoration, more specifically, a method for removing rain from a single image based on a multi-scale fusion generative adversarial network. Background technique [0002] Computer vision is a key technology for automatic driving, video surveillance and other functions, and its effect depends on the quality of the image. In rainy conditions, the captured images and videos are susceptible to the scattering and blurring of raindrops, which makes the image blurred and loses a lot of information, and the decrease in visibility seriously affects the visual effect of image shooting, which greatly affects the outdoor visual effect. . [0003] At the current stage, there are many solutions for rain removal in the restoration of rainy images, and the effect of rain removal is also constantly improving. With the rapid development of machine learning, there are more and more image deraining algorithms based o...

AI Technical Summary

Problems solved by technology

At present, some people in the industry have proposed a method of removing rain from a single image based on a convolutional neural network. This method is not effective for large and dense rainy images, and the resolution of the output image is low, and the visual effect is poor.

In addition, some people use the Pix2Pix network to remove rain from rainy images. The experimental results show that the network still has some unnatural traces in the removal of rainy areas.

The different methods designed for the research of single image deraining can still blur the local area and lose more detail information when repairing the rainy area, so it provides a better single image deraining based on deep learning It is still a problem that those skilled in the art need to study

Images