Abstract | ||
---|---|---|
Recently, algorithms based on the deep neural networks and residual networks have been applied for super-resolution and exhibited excellent performance. In this paper, a multi-branch deep residual network for single image super-resolution (MRSR) is proposed. In the network, we adopt a multi-branch network framework and further optimize the structure of residual network. By using residual blocks and filters reasonably, the model size is greatly expanded while the stable training is also guaranteed. Besides, a perceptual evaluation function, which contains three parts of loss, is proposed. The experiment results show that the evaluation function provides great support for the quality of reconstruction and the competitive performance. The proposed method mainly uses three steps of feature extraction, mapping, and reconstruction to complete the super-resolution reconstruction and shows superior performance than other state-of-the-art super-resolution methods on benchmark datasets. |
Year | DOI | Venue |
---|---|---|
2018 | 10.3390/a11100144 | ALGORITHMS |
Keywords | Field | DocType |
single image super-resolution,deep neural networks,residual networks,peak signal-to-noise ratio,structural similarity index | Residual,Peak signal-to-noise ratio,Evaluation function,Residual Blocks,Algorithm,Feature extraction,Artificial intelligence,Superresolution,Deep neural networks,Mathematics,Machine learning | Journal |
Volume | Issue | Citations |
11 | 10 | 0 |
PageRank | References | Authors |
0.34 | 9 | 3 |