MPIN:a macro-pixel integration network for light field super-resolution

作     者：Xinya WANG Jiayi MA Wenjing GAO Junjun JIANG Xinya WANG;Jiayi MA;Wenjing GAO;Junjun JIANG

作者机构：Electronic Information SchoolWuhan UniversityWuhan 430072China School of Computer Science and TechnologyHarbin Institute of TechnologyHarbin 150001China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2021年第22卷第10期

页      面：1299-1310页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 081202[工学-计算机软件与理论] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Project supported by the National Natural Science Foundation of China(No.61773295) 

主　　题：Light field Super-resolution Macro-pixel representation 

摘      要：Most existing light field(LF)super-resolution(SR)methods either fail to fully use angular information or have an unbalanced performance distribution because they use parts of *** address these issues,we propose a novel integration network based on macro-pixel representation for the LF SR task,named *** the entire LF image simultaneously,we couple the spatial and angular information by rearranging the four-dimensional LF image into a two-dimensional macro-pixel ***,two special convolutions are deployed to extract spatial and angular information,*** fully exploit spatial-angular correlations,the integration resblock is designed to merge the two kinds of information for mutual guidance,allowing our method to be *** the macro-pixel representation,an angular shuffle layer is tailored to improve the spatial resolution of the macro-pixel image,which can effectively avoid *** experiments on both synthetic and real-world LF datasets demonstrate that our method can achieve better performance than the state-of-the-art methods qualitatively and ***,the proposed method has an advantage in preserving the inherent epipolar structures of LF images with a balanced distribution of performance.