Bi-directional Projection Framework for Fast Single Image Super Resolution

作     者：Zhou, Ying Zheng, Zhichao Sun, Quansen 

作者机构：School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer and Electronic Information/School of Artificial Intelligence Nanjing Normal University Nanjing China 

出 版 物：《Recent Patents on Engineering》 (Recent Pat. Eng.)

年 卷 期：2024年第18卷第9期

页      面：152-167页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 070207[理学-光学] 08[工学] 0813[工学-建筑学] 0814[工学-土木工程] 0702[理学-物理学] 

基　　金：This work is supported by the National Natural Science Foundation of China under Grant No. 61673220 and the Natural Science Research of Jiangsu Higher Education Institutions of China under Grant No. 22KJB520021 

主　　题：Mapping 

摘      要：Background: Collaborative Representation (CR) has been widely used in Single Image Super Resolution (SISR) with the assumption that Low-resolution (LR) and high-resolution (HR) features can be linearly represented by neighborhoods and share consistent CR coefficients. Numerous patents and journal papers have been published. However, this CR consistency does not hold in the reconstruction phase, which leads to degraded performance. Methods: To fulfill this gap, we propose a novel bi-directional projection model (BDPM) to establish a bi-directional mapping between LR and HR features without any consistency constraint. The multiple projection matrices are offline computed to reduce reconstruction time greatly. We further develop several strategies to extract features and group neighborhoods such that local structures can be preserved better. Results: Compared to the learning-based methods, BDPM is about 2 to 10 times faster and compared to the reconstruction-based methods, it is about 500 to 2,000 times faster. Conclusion: The empirical studies verify the effectiveness of BDPM and extensive experimental results demonstrate that BDPM achieves better SISR performance than many state-of-the-arts. © 2024 Bentham Science Publishers.