Abstract | ||
---|---|---|
Recently, convolutional neural networks (CNN) have achieved impressive breakthroughs in single image superresolution. In particular, an efficient nonlinear mapping by increasing the depth and width of the network can be learned between the low-resolution input image and the high-resolution target image. However, this will lead to a substantial increase in network parameters, requiring the massive ... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/LSP.2018.2861989 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Training,Image reconstruction,Convolution,Image resolution,Signal resolution,Feature extraction,Dictionaries | Iterative reconstruction,Residual,Pattern recognition,Convolutional neural network,Convolution,Feature extraction,Artificial intelligence,Overfitting,Image resolution,Mathematics,Performance improvement | Journal |
Volume | Issue | ISSN |
25 | 10 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |