基于潜在注意力的高性能视频超分辨率技术  

Efficient Video Super-Resolution with Latent Attention

作　　者：王宇骥 董昊呈 龚雪鸾 陈艳姣 WANG Yuji;DONG Haocheng;GONG Xueluan;CHEN Yanjiao(School of Cyber Science and Engineering,Wuhan University,Wuhan 430070,China;School of Computer Science,Wuhan University,Wuhan 430070,China;College of Electrical Engineering,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]武汉大学国家网络安全学院,武汉430070 [2]武汉大学计算机学院,武汉430070 [3]浙江大学电气工程学院,杭州310058

出　　处：《计算机科学》2023年第S02期216-225,共10页Computer Science

摘　　要：为了解决视频超分辨率的问题,可以对视频中的时空相关性信息加以利用,这是将低分辨率视频重建为高分辨率视频的一种行之有效的方法。之前的相关工作主要集中在利用运动补偿来捕捉视频生成中的时间依赖性,这种阶段性重建策略是低效的。相比运动补偿,注意力模型更能在寻找时空相关性中发挥作用。为了使注意力模型可以被应用于视频超分辨率问题,利用基于摊销变分推理的注意力估计构建潜在注意力模型,并设计了长程注意力模块和短程注意力模块两个有效的注意力功能模块。在此基础上构建出一个新型深度学习网络模型,它可以有效地捕捉视频超分辨率的时空相关性,并允许端到端学习。通过在公共视频数据集的广泛实验,可以证明该方法相比当前最先进的几种方法如SPMC,DUF-16L等具有更优越的性能。To solve the problem of video super-resolution,the spatio-temporal correlation information in videos can be utilized,which is an effective method for reconstructing low resolution videos into high-resolution videos.Prior works mainly focus on utilizing motion compensation to capture temporal dependency in video generation,leading to inefficient stage-wise modeling strategies.Compared to motion compensation,attention model is more efficient in the search for spatio-temporal correlation.In this paper,we formulate a latent attention model for attention estimation with amortized variational inference and instantiate two effective attention modules for video super-resolution.Based on it,a novel deep network model,which can capture spatio-temporal correlations efficiently for video super-resolution and admit end-to-end learning,is presented.Extensive experiments on public video datasets demonstrate the superior performance of our approach over several state-of-the-art methods like SPMC,DUF-16L.

关 键 词：超分辨率 深度学习 潜在注意力 变分推理 高性能 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]