Share Email Print

Proceedings Paper • new

Multi-kernel-based deep residual networks for image super-resolution
Author(s): Jae Woong Soh; Gu Yong Park; Nam Ik Cho
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Single image super-resolution (SISR) is a classical problem in low-level vision task, which aims to find a mapping function from a single low-resolution (LR) input to corresponding high-resolution (HR) output. Recently, deep networks have achieved great success in SISR task. Recent successful deep models mostly consist of stacked the same size convolution filters whose size is mostly 3 by 3. To cope with more variations in both local dependencies and global contexts between LR and HR images, we propose multi-kernel based deep residual networks for SISR. Since larger kernel requires more parameters, we adopt dilated convolution for increasing the size of the receptive field. Also, we adopt local feature fusion, global feature fusion and local residual learning for controlling the multi-scale features and hence for the better performance by accelerating the convergence. Experimental results show that our proposed model yields improved performance.

Paper Details

Date Published: 22 March 2019
PDF: 6 pages
Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 1104908 (22 March 2019); doi: 10.1117/12.2521217
Show Author Affiliations
Jae Woong Soh, Seoul National Univ. (Korea, Republic of)
Gu Yong Park, Seoul National Univ. (Korea, Republic of)
Nam Ik Cho, Seoul National Univ. (Korea, Republic of)

Published in SPIE Proceedings Vol. 11049:
International Workshop on Advanced Image Technology (IWAIT) 2019
Qian Kemao; Kazuya Hayase; Phooi Yee Lau; Wen-Nung Lie; Yung-Lyul Lee; Sanun Srisuk; Lu Yu, Editor(s)

© SPIE. Terms of Use
Back to Top