Back to Search
Start Over
A Real-Time Super-Resolution Method Based on Convolutional Neural Networks.
- Source :
-
Circuits, Systems & Signal Processing . Feb2020, Vol. 39 Issue 2, p805-817. 13p. - Publication Year :
- 2020
-
Abstract
- The aim of single-image super-resolution is to recover a high-resolution image based on a low-resolution image. Deep convolutional neural networks have largely enhanced the reconstruction performance of image super-resolution. Since the input image is always bicubic-interpolated, the main weakness of deep convolutional neural networks is that they are time-consuming. Moreover, fast convolutional neural networks can perform real-time image super-resolution but are unable to achieve reliable performance. To address those drawbacks, we propose a real-time image super-resolution method with good reconstruction performance. We replace the default upsampling method (bicubic interpolation) with a pixel shuffling layer. Local and global residual connections are taken to guarantee better performance. As shown in Fig. 1, our proposed method is not only fast but also accurate. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*IMAGE reconstruction
*HIGH resolution imaging
Subjects
Details
- Language :
- English
- ISSN :
- 0278081X
- Volume :
- 39
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Circuits, Systems & Signal Processing
- Publication Type :
- Academic Journal
- Accession number :
- 141560700
- Full Text :
- https://doi.org/10.1007/s00034-019-01283-y