Paper
18 March 2022 Iterative up and downsampling residual networks for single image super-resolution
Xiaochuan Guo, Chao Xiong, Wen Li
Author Affiliations +
Proceedings Volume 12168, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021); 121680B (2022) https://doi.org/10.1117/12.2631156
Event: International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021), 2021, Harbin, China
Abstract
With the development of neural networks, the effect of single-image super-resolution is getting better. However, in many models that have been proposed, the processing of the upsampling module for image magnification is relatively simple. In this paper, we propose an iterative up and downsampling residual network. We selected a baseline model, and combined the upsampling sub-module and the downsampling sub-module into the final image upsampling module in an iterative form. This module generates detailed differences of the image by connecting convolution and deconvolution, and then extracts them through the residual method to correct the texture of the upsampled image. The iterative module enhances the effect of correction. Experiments on public datasets prove the effectiveness of the model.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaochuan Guo, Chao Xiong, and Wen Li "Iterative up and downsampling residual networks for single image super-resolution", Proc. SPIE 12168, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021), 121680B (18 March 2022); https://doi.org/10.1117/12.2631156
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Super resolution

Convolution

Deconvolution

Image processing

Network architectures

Neural networks

Performance modeling

RELATED CONTENT


Back to Top