Image enhancement method and device, terminal equipment and storage medium

Abstract

The invention provides an image enhancement method and device, terminal equipment and a storage medium, relates to the technical field of deep learning, and can improve the image quality of an enhanced image in an image enhancement task. The image enhancement method comprises the following steps: acquiring a to-be-processed image; inputting a to-be-processed image into a trained image enhancement model for processing, outputting an enhanced image, wherein the image enhancement model comprises a main network and a conditional network, the main network is of a U-net structure, when the to-be-processed image is processed, extracting multiple feature tensors of different scales from the to-be-processed image through the conditional network, and respectively inputting the to-be-processed image and the plurality of feature tensors of different scales into network layers of corresponding scales in the main network for processing to obtain an enhanced image.

Description

technical field [0001] The present application relates to the field of deep learning technology, and in particular to an image enhancement method, device, terminal equipment and storage medium. Background technique [0002] Image enhancement tasks generally include operations such as dehazing, denoising, deraining, super-resolution, decompression artifacts, deblurring, and high dynamic range (High Dynamic Range, HDR) reconstruction. With the wide application of deep learning technology in the fields of image processing and computer vision, how to improve the effect of image enhancement has become the focus of image enhancement tasks based on neural networks. [0003] For example, the network of U-net structure is a special convolutional neural network (Convolutional Neural Networks, CNN for short), although it can well extract the spatial features of different scales of the input image in processing image enhancement tasks. However, the pure U-net structure network cannot s...

AI Technical Summary

Problems solved by technology

However, the pure U-net structure network cannot specifically process the input features, so it is difficult to handle the features with large differences in the enhancement task at the same time, which affects the image enhancement effect, resulting in poor image quality in some areas of the enhanced image.

Images