Image processing and model training method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of computer vision, and provides an image processing and model training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed image, and inputting the to-be-processed image into an image reconstruction model which comprises a feature extraction network and a sub-pixel convolution layer; firstly, a feature extraction network is used for carrying out multi-scale feature extraction on a to-be-processed image and expanding an image channel to obtain a reconstructed feature map, and then a sub-pixel convolution layer is used for amplifying the reconstructed feature map to obtain a reconstructed image. Due to the fact that the feature extraction network can extract multi-scale features and expand image channels, a good reconstruction effect can be obtained without increasing the depth of the network. Meanwhile, a sub-pixel convolutional layer is adopted at the tail end of the model for image amplification, and a feature extraction network is used for processing small-size images, so that the calculation amount and the parameter amount are greatly reduced; therefore, the processing speed is improved while the reconstruction effect is ensured.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular, to an image processing and model training method, device, electronic equipment and storage medium. Background technique [0002] Super-resolution reconstruction refers to the process of restoring a given low-resolution image to a corresponding high-resolution image through specific processing, and is widely used in various fields that need to improve video or image quality, such as video image processing, Medical imaging, remote sensing imaging, video surveillance, etc. [0003] At present, when performing super-resolution reconstruction through deep learning algorithms, it is necessary to use a network with a sufficiently deep number of layers to obtain better reconstruction results. Therefore, the network structure is usually very complex, and the amount of calculation is large, which affects the processing speed. Contents of the invention [0004] The purpos...

AI Technical Summary

Problems solved by technology

[0003] At present, when performing super-resolution reconstruction through deep learning algorithms, it is necessary to use a network with a sufficiently deep number of layers to obtain a better reconstruction effect. Therefore, the network structure is usually very complex, and the amount of calculation is large, which affects the processing speed.

Images