Image super-resolution reconstruction algorithm based on multi-level continuous encoding and decoding

被引：0
|
作者：
Song Z.-Y. [1 ,2 ,3 ]
Zhao X.-Q. [1 ,2 ,3 ]
Hui Y.-Y. [1 ,2 ,3 ]
Jiang H.-M. [1 ,2 ,3 ]
机构：
[1] College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou
[2] Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou
[3] National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2023年 / 57卷 / 09期
关键词：
attention; convolutional neural network; multi-level continuous encoding and decoding; multi-level feature information; super-resolution reconstruction;
D O I：
10.3785/j.issn.1008-973X.2023.09.020
中图分类号：
学科分类号：
摘要：
A new image super-resolution reconstruction algorithm was proposed, aiming at the problem that the image super-resolution reconstruction algorithms by using convolutional neural network as the model framework was difficult to extract multi-level feature information inside a low-resolution image, resulting in the lack of rich details in the reconstructed image. The proposed algorithm extracted shallow features from low-resolution images through initial convolution layer. Image features of different levels in a low-resolution image were obtained through a plurality of end-to-end connected multi-level continuous encoding and decoding attention residual modules, the weights of these features were generated according to different extraction difficulties, and the image features of different levels were recalibrated to obtain rich detailed features in the image. Through the up-sampling module and reconstruction convolution layer, the extracted rich detailed features and shallow features were reconstructed into high-resolution images. The comparative test results on the test sets of Set5, Set14, BSD100 and Urban100 show that the image reconstructed by the proposed algorithm is superior to the image reconstructed by a mainstream algorithm in objective evaluation index and visual effect. © 2023 Zhejiang University. All rights reserved.
引用
收藏
页码：1885 / 1893
页数：8
相关论文
共 31 条
  • [1] CHEN H, HE X, QING L, Et al., Real-world single image super-resolution: a brief review [J], Information Fusion, 79, pp. 124-145, (2022)
  • [2] REBECQ H, RANFTL R, KOLTUN V, Et al., Events-to-video: bringing modern computer vision to event cameras [C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3857-3866, (2019)
  • [3] WANG Z, JIANG K, YI P, Et al., Ultra-dense GAN for satellite imagerysuper-resolution [J], Neurocomputing, 398, pp. 328-373, (2020)
  • [4] LIU H, GU Y, WANG T, Et al., Satellite video super-resolution based on adaptively spatiotemporal neighbors and nonlocal similarity regularization [J], IEEE Transactions on Geoscience and Remote Sensing, 58, 12, pp. 8372-8383, (2020)
  • [5] YUE L, SHEN H, LI J, Et al., Image super-resolution: the techniques, applications, and future [J], Signal Processing, 128, pp. 389-408, (2016)
  • [6] DENG L, YU D., Deep learning: methods and applications [M], Now Foundations and Trends, pp. 197-387, (2014)
  • [7] JORDAN M I, MITCHELL T M., Machine learning: trends, perspectives, and prospects [J], Science, 349, 6245, pp. 255-260, (2015)
  • [8] LECUN Y, BENGIO Y, HINTON G., Deep learning [J], Nature, 521, pp. 436-444, (2015)
  • [9] ANWAR S, KHAN S, BARNES N., A deep journey into super-resolution: a survey [J], ACM Computing Surveys, 53, 3, pp. 1-34, (2020)
  • [10] WANG Z, CHEN J, HOI S C H., Deep learning for image super-resolution: a survey [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 10, pp. 3365-3387, (2021)
1234