Super-resolution reconstruction method based on a fused multi-level feature map

Abstract

The invention discloses a super-resolution reconstruction method based on fusion of a multi-level feature map, and the method comprises the following steps of employing the idea of a dense network toconstruct a feature extraction network for generating the multi-level feature map; performing dimensionality reduction on the connected feature map by using a convolutional neural network with a convolution kernel size of 1 * 1, fusing the feature map, performing feature extraction of the network on the basis to obtain a fused multi-level feature map, and using a sub-pixel convolutional neural network as an upsampling operator to obtain a high-resolution reconstructed image. In the training process, a perception loss function is used as a minimization target to generate a high-resolution imagemore conforming to visual perception. According to the method, the defect that an existing super-resolution reconstruction algorithm cannot fully utilize a multi-level feature map is overcome, localand overall information in a low-resolution image obtained by a feature extraction network can be fully utilized, and a high-resolution image can be accurately and quickly reconstructed from the low-resolution image.

Description

technical field [0001] The invention relates to a super-resolution reconstruction method based on fusing multi-level feature maps, and belongs to the technical field of computer vision. Background technique [0002] Single image super-resolution (SISR), as a fundamental low-level computer vision problem, has received increasing attention from the research and artificial intelligence communities. The goal of SISR is to recover high-resolution (HR) images from single low-resolution (LR) images. Since the pioneering work of SRCNN was proposed in the literature (Image Super-Resolution Using Deep Convolutional Networks[J].IEEETransactions on Pattern Analysis and Machine Intelligence, 2014, 38(2), the deep convolutional neural network (CNN) method has brought booming. Various network structure designs and training strategies have continuously improved SR performance, especially in the peak signal-to-noise ratio (PSNR) accuracy evaluation index, which has achieved a huge improvem...

AI Technical Summary

Problems solved by technology

However, these PSNR-oriented methods tend to output overly smooth results without enough high-frequency details, since the PSNR metric is basically inconsistent with the subjective evaluation of human observers

Images