Joint task learning method for super-resolution and perception image enhancement of single image

Abstract

The invention discloses a joint task learning method for super-resolution and perception image enhancement of a single image, and the method comprises usually carrying out the hybrid combination of asuper-resolution task and a perception image enhancement task for the actual demands in an actual scene, and obtaining a high-quality high-resolution enhanced image from a low-resolution original image. The invention provides a super resolution and perception image enhancement task joint learning framework named Dep SR-PIE. The framework comprises a multi-path super-resolution network (MSRnet), adetail complementary network (DCN) and a hybrid U-net enhancement network (FULENet). The MSRnet utilizes a multipath learning strategy to describe local and global information at the same time, the DCN utilizes double bypass shared convolution to sample and enhance high-frequency details, and the FULENet seeks an optimal fusion color correction matrix to learn color and tone mapping. Through quantitative and qualitative evaluation of the four data sets, a conclusion that most indexes of a joint learning framework are superior to those of a comparison method can be obtained. Through the methodprovided by the invention, a high-quality high-resolution enhanced image can be obtained more quickly and efficiently.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to a joint task learning method of single image super-resolution and perceptual image enhancement. Background technique [0002] Image super-resolution and perceptual image enhancement are major research topics in computer vision and image processing. In recent years, deep learning techniques have achieved impressive results in various computer vision tasks, greatly promoting the development of super-resolution and perceptual image enhancement. In order to solve the super-resolution task, a variety of deep learning methods based on traditional convolutional neural networks and Generative Adversarial Networks (GAN, Generative Adversarial Networks) have been developed. For perceptual image enhancement tasks, a series of automatic processing methods are developed to deal with issues such as color reproduction, image sharpness, brightness and contrast. For the joint probl...

AI Technical Summary

Problems solved by technology

However, this sequential approach is inefficient and inaccurate because errors are propagated in the cascading process

Images