Image super-resolution reconstruction method and device, electronic equipment and storage medium

Abstract

The invention discloses an image super-resolution reconstruction method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-processed image; inputting the to-be-processed image into the super-resolution reconstruction model to enable the super-resolution reconstruction model to predict each pixel point in the to-be-processed image, and obtaining a super-resolution reconstruction image of the to-be-processed image; enabling the super-resolution reconstruction model to be a binary neural network model obtained by training a plurality of training samples in advance, wherein each training sample comprises a first resolution image block and a corresponding second resolution image block, and the second resolution ratio is greater than the first resolution ratio. The double-flow binary reasoning layer in the super-resolution reconstruction model can improve the binary quantization precision through a quantization threshold value and improve the information bearing capacity of the super-resolution reconstruction model through a double-flow network structure, so that the performance of the super-resolution reconstruction model can be remarkably improved; and meanwhile, the reconstruction speed can be improved on the basis of ensuring the image reconstruction precision.

Description

technical field [0001] The invention belongs to the field of machine learning, and in particular relates to an image super-resolution reconstruction method, device, electronic equipment and storage medium. Background technique [0002] As a low-cost and easy-to-operate image quality enhancement method, image super-resolution reconstruction has been widely used in many fields such as digital media, medical imaging, satellite remote sensing, and video surveillance. [0003] In order to minimize model storage and computing resources, binary neural networks are usually used in related technologies to achieve super-resolution reconstruction of images on mobile devices with low computing performance such as mobile phones. value to reduce storage resource consumption during model deployment. [0004] However, the binary neural network in the related art includes a full-precision upsampling layer. The complex calculation process of the full-precision number in this layer not only b...

AI Technical Summary

Problems solved by technology

[0004] However, the binary neural network in the related art includes a full-precision upsampling layer. The complex calculation process of the full-precision number in this layer not only brings a huge computational burden to the model, but also reduces the quality of the reconstructed image due to its limited information carrying capacity.

Images