Single image super-resolution reconstruction method combining depth learning and gradient transformation

Abstract

The invention discloses a single image super-resolution reconstruction method combining depth learning and gradient transformation. The method comprises the steps that a super-resolution method based on depth learning is used to carry out upsampling on an input low-resolution image to acquire an upsampling image; a gradient operator is used to carry out gradient-extracting on the upsampling image; a depth convolutional neural network is used to convert extracted gradient; a cost function is reconstructed by using the input low-resolution image and the converted gradient as constraints; a gradient descent method is used to optimize the reconstructed cost function to acquire a final output high-resolution image. According to the single image super-resolution reconstruction method provided by the invention, the reconstructed image has a fine structure in the subjective visual effect, is free of artificial effect, and has a high objective evaluation parameter value. The invention provides the effective single image super-resolution reconstruction method.

Description

technical field [0001] The invention relates to image super-resolution reconstruction technology, in particular to a single image super-resolution reconstruction method combined with deep learning and gradient transformation, belonging to the field of digital image processing. Background technique [0002] In real life, due to the limitation of imaging equipment and imaging environment, as well as the loss of image information in the transmission process, the images acquired by people are often of low resolution and low quality, which is difficult to meet the needs. Image super-resolution reconstruction technology is a technology that reconstructs input low-resolution images into high-resolution images through signal processing technology without increasing hardware costs. The image reconstructed by image super-resolution reconstruction technology is not only better than the input image in spatial resolution, but also has a significant improvement in subjective visual effect...

AI Technical Summary

Problems solved by technology

The super-resolution method based on the gradient prior can effectively remove the ringing effect and the jagged effect of the reconstructed image, but this type of method cannot reconstruct the details and fine structures of the image very well.

Images