15 November 2017 Deep residual networks of residual networks for image super-resolution
Author Affiliations +
Proceedings Volume 10605, LIDAR Imaging Detection and Target Recognition 2017; 106053I (2017) https://doi.org/10.1117/12.2295691
Event: LIDAR Imaging Detection and Target Recognition 2017, 2017, Changchun, China
Abstract
Single image super-resolution (SISR), which aims at obtaining a high-resolution image from a single low-resolution image, is a classical problem in computer vision. In this paper, we address this problem based on a deep learning method with residual learning in an end-to-end manner. We propose a novel residual-network architecture, Residual networks of Residual networks (RoR), to promote the learning capability of residual networks for SISR. In residual network, the signal can be directly propagated from one unit to any other units in both forward and backward passes when using identity mapping as the skip connections. Based on it, we add level-wise connections upon original residual networks, to dig the optimization ability of residual networks. Our experiments demonstrate the effectiveness and versatility of RoR, it can get a faster convergence speed and gain higher resolution accuracy from considerably increased depth.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xueqi Wei, Xueqi Wei, Fumeng Yang, Fumeng Yang, Congzhong Wu, Congzhong Wu, } "Deep residual networks of residual networks for image super-resolution", Proc. SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017, 106053I (15 November 2017); doi: 10.1117/12.2295691; https://doi.org/10.1117/12.2295691
PROCEEDINGS
6 PAGES


SHARE
Back to Top