Affiliation:
1. Xi’an Research Institute of High-Tech, Shaanxi 710025, China
Abstract
The convolutional neural network has achieved good results in the superresolution reconstruction of single-frame images. However, due to the shortcomings of infrared images such as lack of details, poor contrast, and blurred edges, superresolution reconstruction of infrared images that preserves the edge structure and better visual quality is still challenging. Aiming at the problems of low resolution and unclear edges of infrared images, this work proposes a two-stage generative adversarial network model to reconstruct realistic superresolution images from four times downsampled infrared images. In the first stage of the generative adversarial network, it focuses on recovering the overall contour information of the image to obtain clear image edges; the second stage of the generative adversarial network focuses on recovering the detailed feature information of the image and has a stronger ability to express details. The infrared image superresolution reconstruction method proposed in this work has highly realistic visual effects and good objective quality evaluation results.
Subject
Electrical and Electronic Engineering,Media Technology,Communication
Reference40 articles.
1. Infrared imaging system and applications;L. Xiang-di;Laser & Infrared,2014
2. Infrared super-resolution imaging based on compressed sensing
3. Infrared super-resolution imaging method based on retina micro-motion
4. An overview of computational photography;J. L. Suo;Science China(Information Sciences),2012
5. Learning a Deep Convolutional Network for Image Super-Resolution;D. Chao,2014
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献