期刊
IEEE ACCESS
卷 9, 期 -, 页码 98790-98799出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3083577
关键词
Image reconstruction; Image resolution; Wavelet transforms; Training; Wavelet domain; Superresolution; Convolutional neural networks; Deep learning; space domain; loss function; super resolution algorithm; wavelet domain
资金
- National Science Foundation of China [61475187]
This paper proposes an image super resolution algorithm combining deep learning and wavelet transform (ISRDW) that effectively captures image details, reduces training model difficulty with cross-connection and residual learning, and achieves better results through loss function constraint in network training.
In order to further improve the reconstruction effect of the image super resolution algorithm, this paper proposes an image super resolution algorithm combining deep learning and wavelet transform (ISRDW). In terms of network design, it is not only simple in structure, but also more effective in capturing image details compared with other neural network structures. At the same time, cross-connection and residual learning methods are used to reduce the difficulty of the training model. In terms of loss function, this paper uses the loss generated in the original image space domain and the wavelet domain to strengthen the constraint of network training. Experimental results show that the algorithm proposed in this paper achieves better results under different data sets and different evaluation indexes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据