Name
Abstract | ||
|---|---|---|
Progresses has been witnessed in single image superresolution in which the low-resolution images are simulated by bicubic downsampling. However, for the complex image degradation in the wild such as downsampling, blurring, noises, and geometric deformation, the existing superresolution methods do not work well. Inspired by a persistent memory network which has been proven to be effective in image restoration, we implement the core idea of human memory on the deep residual convolutional neural network. Two types of memory blocks are designed for the NTIRE2018 challenge. We embed the two types of memory blocks in the framework of enhanced super resolution network (EDSR), which is the NTIRE2017 champion method. The residual blocks of EDSR is replaced by two types of memory blocks. The first type of memory block is a residual module, and one memory block contains four residual modules with four residual blocks followed by a gate unit, which adaptively selects the features needed to store. The second type of memory block is a residual dilated convolutional block, which contains seven dilated convolution layers linked to a gate unit. The two proposed models not only improve the super-resolution performance but also mitigate the image degradation of noises and blurring. Experimental results on the DIV2K dataset demonstrate our models achieve better performance than EDSR. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/CVPRW.2018.00125 | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
Keywords | Field | DocType |
complex image degradation,persistent memory network,image restoration,deep residual convolutional neural network,enhanced super resolution network,residual dilated convolutional block,persistent memory residual network,single image super resolution,NTIRE2018 challenge,bicubic downsampling,gate unit,DIV2K dataset,EDSR | Iterative reconstruction,Computer vision,Residual,Computer science,Convolutional neural network,Convolution,Bicubic interpolation,Artificial intelligence,Image restoration,Upsampling,Image resolution | Conference |
ISSN | ISBN | Citations |
2160-7508 | 978-1-5386-6101-7 | 1 |
PageRank | References | Authors |
0.35 | 4 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rong Chen | 1 | 55 | 10.48 |
| Yanyun Qu | 2 | 216 | 38.66 |
| Kun Zeng | 3 | 116 | 5.48 |
| Jinkang Guo | 4 | 2 | 0.73 |
| Cui-Hua Li | 5 | 74 | 13.24 |
| Yuan Xie | 6 | 407 | 27.48 |