Image rain removal model training method, image rain removal method and device

Abstract

The embodiment of the invention provides an image rain removal model training method, an image rain removal method and equipment, in order to eliminate long rain stripes, a recursive convolution structure is used, feature vectors of an input image with rain stripes are extracted through a plurality of convolution kernels, and vector fusion is carried out, so that the long rain stripes are eliminated. And the fusion feature vector and the feature vector of the input image are added and are output through the LSTM network module, so that long-distance context information can be better linked, and the receptive field can be expanded. And comparing the output feature vector with the feature vector of the corresponding rain-free image, if the comparison result is not a preset result, adjusting the parameter of the recursive convolution module according to the comparison result, and re-executing the operation, that is, through cyclic convolution, enabling the model to learn the internal relation between the cross-stage features, better recovering the details of the image, and improving the image quality. Moreover, the size of the model is effectively reduced, and a good rain removal effect can be achieved on portable embedded equipment and mobile equipment with insufficient memory and computing power.

Description

technical field [0001] The embodiments of the present application relate to the technical field of computer vision, and in particular, to an image deraining model training method, an image deraining method and equipment. Background technique [0002] The research on deraining images or videos has always been an important topic in the field of computer vision and image processing. In real life, because rain and snow will block the road conditions to a certain extent, it is very dangerous to drive a vehicle in severe weather with heavy rain or snow; Due to the occlusion of snow, it is impossible to provide enough information to the relevant personnel to determine the identity of the target; in addition, people will take a lot of pictures of beautiful scenery when they travel, but some pictures cannot be clearly seen due to weather conditions and other reasons. Effect. The above-mentioned situations all require post-processing of the image, so the research on image deraining ...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides an image deraining model training method, image deraining method and equipment to overcome the loss of a large number of image details after deraining the existing image with heavy rain streaks, resulting in white spots in the derained image The problem

Images