RealFuVSR:Feature enhanced real-world video super-resolution  

作　　者：Zhi LI Xiongwen PANG Yiyue JIANG Yujie WANG 

机构地区：[1]School of Artificial Intelligence,South China Normal University,Guangzhou 510631,China [2]School of Computer Science,South China Normal University,Guangzhou 510631,China [3]School of Economics and Management,South China Normal University,Guangzhou 510631,China

出　　处：《Virtual Reality & Intelligent Hardware》2023年第6期523-537,共15页虚拟现实与智能硬件（中英文）

基　　金：Supported by Open Project of the Ministry of Industry and Information Technology Key Laboratory of Performance and Reliability Testing and Evaluation for Basic Software and Hardware。

摘　　要：Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.

关 键 词：Video super-resolution Deformable convolution Cascade residual upsampling Second-order degradation Multi-scale feature extraction 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]