Online multi-frame super-resolution of image sequences

作     者：Xu, Jieping Liang, Yonghui Liu, Jin Huang, Zongfu Liu, Xuewen 

作者机构：Space Engn Univ 1 Bayi Rd Beijing 101416 Peoples R China Natl Univ Def Technol Coll Optoelect Sci & Engn 109 Deya Rd Changsha 410073 Hunan Peoples R China 

出 版 物：《EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING》 (国际影象与视频处理杂志)

年 卷 期：2018年第2018卷第1期

页      面：1页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：National Science Fund for Outstanding Young Scholars [2017-JCJQ-ZQ-005] 

主　　题：Super-resolution Image processing Image sequences Online image processing 

摘      要：Multi-frame super-resolution recovers a high-resolution (HR) image from a sequence of low-resolution (LR) images. In this paper, we propose an algorithm that performs multi-frame super-resolution in an online fashion. This algorithm processes only one low-resolution image at a time instead of co-processing all LR images which is adopted by state-of-the-art super-resolution techniques. Our algorithm is very fast and memory efficient, and simple to implement. In addition, we employ a noise-adaptive parameter in the classical steepest gradient optimization method to avoid noise amplification and overfitting LR images. Experiments with simulated and real-image sequences yield promising results.