Image reconstruction system and method based on CRC-SAN network

Abstract

The invention relates to the technical field of image super-resolution reconstruction, in particular to an image reconstruction system and method based on a cross residual channel-spatial attention network. The system comprises a shallow feature extraction module, a depth feature extraction module, an up-sampling module and a reconstruction layer. The input of the shallow feature extraction moduleis a low-resolution image, and the shallow feature extraction module is used for extracting shallow features; the depth feature extraction module comprises a frequency division module and a cross residual group, the input of the depth feature extraction module is the output of the shallow feature module, and the depth feature extraction module is used for extracting deep features; the input of the up-sampling module is a deep feature and is used for up-sampling; and the reconstruction layer is used for reconstructing features to obtain a high-resolution image. The reconstruction network provided by the invention has stronger feature expression capability and differentiated learning capability, and can reconstruct a high-quality high-resolution image.

Description

technical field [0001] The invention relates to the technical field of image super-resolution reconstruction, in particular to an image reconstruction system and method based on a cross residual channel-spatial attention CRCSAN network. Background technique [0002] Single-image super-resolution reconstruction means upsampling a low-resolution image to a corresponding scale to obtain a high-resolution image. [0003] Super-resolution reconstruction of a single image is a serious pathological problem, because there may be multiple different high-resolution images corresponding to a single low-resolution image during the process of resolution increase, in other words, there will be There are multiple solutions. Therefore, in order to solve the above problems, a large number of single image super-resolution reconstruction methods based on convolutional neural networks have been proposed. However, in the existing single-image super-resolution reconstruction methods based on co...

AI Technical Summary

Problems solved by technology

However, in the existing single-image super-resolution reconstruction methods based on convolutional neural networks, most methods ignore the differences in features between different components in the image, but treat the features of different components in the image equally. The network lacks the ability to distinguish learning, which hinders the performance improvement of convolutional neural networks

Therefore, the performance of existing single image super-resolution methods based on convolutional neural networks still has a large room for improvement.

Images