区域感知实时人像超分辨率重建网络  

Region-aware real-time portrait super resolution reconstruction network

作　　者：龚柯存 周梦琳 唐东明[1,2] GONG Kecun;ZHOU Menglin;TANG Dongming(Key Laboratory for Computer Systems of National Ethnic Affairs Commission,Southwest Minzu University,Chengdu 610041,China;School of Computer Science and Engineering,Southwest Minzu University,Chengdu 610041,China;School of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China)

机构地区：[1]西南民族大学国家民族事务委员会计算机系统重点实验室,成都610041 [2]西南民族大学计算机科学与工程学院,成都610041 [3]成都信息工程大学软件工程学院,成都610225

出　　处：《北京航空航天大学学报》2024年第2期588-595,共8页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(61873217);四川省科技计划(2021JDRC0063);西南民族大学中央高校基本科研业务费专项资金(校2021118)。

摘　　要：在人像超分辨率重建领域,传统方法通常将整幅图像进行统一处理,导致效率低下。为降低模型的推理时延,提出了一种实时超分辨率重建模型RASR。该模型利用门控单元处理低分辨率图像,识别出人像边缘区域;采用分区重建策略,使用不同尺寸的子模型分别针对包含或不包含人像边缘的区域进行重建。实验结果表明:与现有方法相比,RASR模型在4倍上采样重建场景下的推理时延降低了88%,能够更有效地重建高分辨率人像图像。Conventional techniques typically process the entire image uniformly,which leads to low efficiency in the field of portrait super-resolution reconstruction.To reduce the inference latency of the model,this research proposes a real-time super-resolution reconstruction model RASR.The model first uses gating unit to process the low-resolution images and identify the edge of the portrait.Then,a partition reconstruction strategy is adopted,and sub-models of different sizes are used to reconstruct the areas containing or not containing the portrait edge,respectively.The experimental results show that the RASR model is able to reconstruct high-resolution portrait images more efficiently by reducing the inference latency of the RASR model by 88%in a 4-foldsampling reconstruction scene compared to the existing methods.

关 键 词：区域感知 单图像超分辨率 门控单元 通道划分块 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]