Single-image blind motion blur removing method based on multi-scale residual generative adversarial network

Abstract

The invention discloses a single-image blind motion blur removing method based on a multi-scale residual generative adversarial network. The method comprises the following steps: acquiring a GoPRo paired data set, and connecting the GoPRo paired data set to form an image pair in a fuzzy-clear form; randomly cutting the training image into an image patch with the size of 256 * 256; taking the standardized image as model training input data; designing a convolutional neural network, and outputting a deblurred image; calculating the peak signal-to-noise ratio and structural similarity of the output information of the model and the clear image of the corresponding label, and performing loss optimization; and deblurring a picture with a motion blur scene in reality by using the optimized modelparameters to obtain a corresponding clear picture. Based on the convolutional neural network, the conditional generative adversarial network is adopted as a backbone network, and the fine-grained residual module is adopted as a main body module, so that the breakthrough of converting an image deblurring problem into an image translation problem and solving the image deblurring problem is realized, and important technical support is provided for subsequent operation of image deblurring.

Description

technical field [0001] The invention relates to the technical field of convolutional neural network and image blind motion blur removal, in particular to a single image blind motion blur removal method based on multi-scale residual generative confrontation network. Background technique [0002] With the rapid development of science and technology, photographic equipment such as smart phones and digital cameras have become widely popularized, making the acquisition and dissemination of images very simple. In the process of taking pictures, due to the shaking of the photographer's hand, the camera moves during the exposure process or the object is moved during the camera exposure process, resulting in motion blur in the image, which ultimately affects the image in various fields such as image semantic segmentation and detection. application. Therefore, as a kind of image restoration technology, the topic of removing motion blur in images is also of great application research ...

AI Technical Summary

Problems solved by technology

But the difficulty of both methods lies in how to make the network reconstruct the blurred picture more quickly while ensuring a better reconstruction effect.

Images