Image super-resolution model training method and device and image super-resolution model reconstruction method and device

Abstract

The invention provides an image super-resolution model training method and device and an image super-resolution model reconstruction method and device. The training method comprises the steps of: obtaining a training sample set; inputting the low-resolution images in the training sample set into a preset image super-resolution model to obtain alternative high-resolution images; respectively performing image mode conversion on the alternative high-resolution image and the real high-resolution image to obtain corresponding visible light images; and constructing a loss function based on the difference between the two groups of visible light images and the real visible light image and the difference between the alternative high-resolution image and the real high-resolution image, and performing model training on a preset image super-resolution model. Mapping errors of alternative high-resolution images and corresponding real high-resolution images are calculated in a visible light space toserve as feedback information to participate in model training, so that the trained preset image super-resolution model can output high-fidelity high-resolution images under the condition of large-scale magnification times.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image super-resolution model training method, reconstruction method and device. Background technique [0002] Image can be divided into optical image and non-visible light image in terms of imaging principle. Among them, non-visible light image is widely used in military, earth remote sensing observation, agriculture and other fields. Due to the limitations of imaging equipment, non-visible light images such as: synthetic aperture radar (Synthetic Aperture Radar, referred to as SAR) images, SAR imaging system has many advantages, such as work is not limited by time, climate and other conditions, can penetrate a certain surface coverage for remote sensing observations. Therefore, SAR images are widely used in various fields, such as military target reconnaissance and long-range strikes, marine environment monitoring, earth resource exploration, monitoring of various n...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present invention provides an image super-resolution model training method, reconstruction method and device to overcome the lack of image super-resolution reconstruction suitable for large-scale magnification in the prior art

Images