Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6941574 | Signal Processing: Image Communication | 2018 | 12 Pages |
Abstract
Due to excellent self-learning ability, deep convolutional neural networks (CNNs) are successfully employed in the field of single image super-resolution (SR) compared with interpolation methods and sparse coding methods. To implement the multi-scale image SR task with a single trained model and to further improve the performance of image SR, we propose a novel cascaded CNN framework with three stages, which are feature extraction, detail prediction and reconstruction. At the stage of feature extraction, we propose a scheme of multi-scale feature mapping to extract the inherent features via the low-resolution image. At the stage of detail prediction, the lost details of the original low-resolution image are predicted via the network cascade. Finally, a high-resolution image is achieved by the scheme of residual learning, which is implemented by superimposing the lost details and the original low-resolution image. To avoid gradient explosions, we use gradient clipping to train the proposed cascaded CNN framework. Comparison results indicate that our proposed cascaded CNN framework for image SR is superior to many state-of-the-art methods.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Fu Zhang, Nian Cai, Guandong Cen, Feiyang Li, Han Wang, Xindu Chen,