Second-order progressive feature fusion network for image super-resolution reconstruction

被引：0
|
作者：
Yu L. [1 ]
Deng Q. [1 ]
Zheng L. [2 ]
Wu H. [1 ]
机构：
[1] School of Information and Communication Engineering, Harbin Engineering University, Harbin
[2] School of Computer Science and Technology, Harbin Engineering University, Harbin
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2024年 / 46卷 / 02期
关键词：
convolutional neural network (CNN); feature fusion; second-order feature fusion mechanism; super-resolution reconstruction;
D O I：
10.12305/j.issn.1001-506X.2024.02.03
中图分类号：
学科分类号：
摘要：
Some super-resolution networks ignore the reuse of the features of different levels, and there is no fusing of the features. In order to solve those problems, a second-order progressive feature fusion super-resolution network with strong feature reuse and fuse ability is constructed to realize the reconstructed image with high resolution and high fidelity. The core of the network is progressive feature fusion block. Progressive feature fusion block enhances the reuse of features through feature fusion operation. In addition, a second-order feature fusion mechanism is proposed, which adopts progressive feature fusion method for feature fusion at the local and global levels of the network. The experimental results show that the reconstructed image of the network is clearer than that of other networks on line and contour, and better results are obtained in peak signal to noise ratio (SNR) and structural similarity. For example, when the scaling factor is 2, the peak SNR/ structure similarity on each test set is 38. 20 dB/0. 961 2, 33. 81 dB/0. 919 5, 32. 28 dB/0. 901 0, 32. 65 dB/ 0.932 4, and 39. 11 dB/0. 977 9 respectively, which proves that the proposed model acheives improvent compared to other models. The advantages of the second-order progressive feature fusion super-resolution network is proven from the objective standard and subjective point of view. © 2024 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：391 / 400
页数：9
相关论文
共 28 条
  • [1] LIU A R, LIU Y H, GU J J, Et al., Blind image super-resolution
  • [2] a survey and beyond[J], IEEE Trans, on Pattern Analysis and Machine Intelligence, 45, 5, pp. 5461-5480, (2022)
  • [3] TIAN C W, ZHANG X Y, LIN J C W, Et al., Generative adversarial networks for image super-resolution
  • [4] a survey
  • [5] BI D Y, WANG S P, LIU K, Et al., Super-resolution algorithm based on parallel mapping convolution network, Systems Engineering and Electronics, 40, 8, pp. 1873-1880, (2018)
  • [6] TAO H J, LU X B., Contour-based smoky vehicle detection from surveillance video for alarm systems[J], Signal, Image and Video Processing, 13, 2, pp. 217-225, (2019)
  • [7] WANG G, ZHOU R F, ZOU Y K., Research on image optimization technology based on compressed sensing [J], Journal of Electronics &. Information Technology, 42, 1, pp. 222-233, (2020)
  • [8] CHEN S Z, CAO S P, GUI M Y, Et al., Image blind deblurring algorithm based on deep multi-level wavelet transform, Journal of Electronics &. Information Technology, 43, 1, pp. 154-161, (2021)
  • [9] CHEN H G, HE X H, Q1NG L B, Et al., Real-world single image super resolution
  • [10] a brief review, Information Fusion, 79, pp. 124-145, (2022)
123