Inception learning super-resolution

Abstract

An efficient network for super-resolution, which we refer to as inception learning super-resolution (ILSR), is proposed. We adopt the inception module from GoogLeNet to exploit multiple features from low-resolution images, yet maintain fast training steps. The proposed ILSR network demonstrates low computation time and fast convergence during the training process. It is divided into three parts: feature extraction, mapping, and reconstruction. In feature extraction, we apply the inception module followed by dimensional reduction. Then, we map features using a simple convolutional layer. Finally, we reconstruct the high-resolution component using the inception module and a $1\times 1$ convolutional layer. Experimental results demonstrate that the proposed network can construct sharp edges and clean textures, and reduce computation time by up to three orders of magnitude compared to state-of-the-art methods.

© 2017 Optical Society of America

Terahertz image super-resolution based on a deep convolutional neural network

Zhenyu Long, Tianyi Wang, ChengWu You, Zhengang Yang, Kejia Wang, and Jinsong Liu
Appl. Opt. 58(10) 2731-2735 (2019)

Joint artifact correction and super-resolution of image slicing and mapping system via a convolutional neural network

Anqi Liu, Xianzi Zeng, Yan Yuan, Lijuan Su, and Wanyue Wang
Opt. Express 29(5) 7247-7260 (2021)

Rapid super resolution for infrared imagery

Navot Oz, Nir Sochen, Oshry Markovich, Ziv Halamish, Lena Shpialter-Karol, and Iftach Klapp
Opt. Express 28(18) 27196-27209 (2020)

Pixel super-resolution for lens-free holographic microscopy using deep learning neural networks

Zhenxiang Luo, Abdulkadir Yurt, Richard Stahl, Andy Lambrechts, Veerle Reumers, Dries Braeken, and Liesbet Lagae
Opt. Express 27(10) 13581-13595 (2019)

How to deal with color in super resolution reconstruction of images

Rui Gong, Yi Wang, Yilin Cai, and Xiaopeng Shao
Opt. Express 25(10) 11144-11156 (2017)