Image reconstruction method and device, equipment and storage medium

Abstract

The invention belongs to the field of digital image processing, and particularly relates to an image reconstruction method, device and equipment and a storage medium, and the method comprises the steps: obtaining a pre-trained image reconstruction model, and enabling a first network branch in the image reconstruction model to be used for generating an initial reconstruction image based on first image data; the second network branch is used for extracting a color correction coefficient from the second image data; the output layer is used for adjusting the initial reconstruction image by using the color correction coefficient; inputting the first image data and the second image data into an image reconstruction model to obtain a reconstructed image; the problem that the image reconstruction effect is poor due to the fact that a traditional image reconstruction model cannot recover image data collected in a dark area or a bright area in a wide dynamic scene can be solved. The image sensor is used for collecting the first image data to reconstruct the image, it can be guaranteed that the reconstructed image does not lose details of the bright and dark part, meanwhile, the second image data is used for extracting the color correction coefficient for color adjustment, and the perception effect of the reconstructed image can be improved.

Description

【Technical field】 [0001] The invention belongs to the field of digital image processing, and in particular relates to an image reconstruction method, device, equipment and storage medium. 【Background technique】 [0002] Image reconstruction refers to the process of reconstructing the original image data collected by the image acquisition device into an image with better light and dark details. [0003] The traditional image reconstruction method includes: obtaining the original image data collected by the image sensor, performing image signal processing on the original image data to obtain the processed image data; inputting the processed image data into the pre-trained image reconstruction model to obtain The reconstructed image. Wherein, the image reconstruction model is trained by using sample images that have undergone image signal processing. [0004] However, the sample images processed by the image signal usually lose the information of the dark or bright areas of t...

AI Technical Summary

Problems solved by technology

[0005] The application provides an image reconstruction method, device, equipment and storage medium, which can solve the problem that the trained image reconstruction model cannot recover image data collected in dark or bright areas in wide dynamic scenes, resulting in poor image reconstruction effect

Images