S2A: Scale-Attention-Aware Networks for Video Super-Resolution

Entropy

Tao Dai¹  Zexuan Zhu¹  Taian Guo¹  Ling Liu¹  Shu-Tao Xia² 

[1] College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China;Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing 100084, China;

关键词: scale-and-attention-aware;    criss-cross channel attention;    video super-resolution;   

DOI  :  10.3390/e23111398

来源: DOAJ

【 摘 要 】

Convolutional Neural Networks (CNNs) have been widely used in video super-resolution (VSR). Most existing VSR methods focus on how to utilize the information of multiple frames, while neglecting the feature correlations of the intermediate features, thus limiting the feature expression of the models. To address this problem, we propose a novel SAA network, that is, Scale-and-Attention-Aware Networks, to apply different attention to different temporal-length streams, while further exploring both spatial and channel attention on separate streams with a newly proposed Criss-Cross Channel Attention Module ($C^{3}AM$). Experiments on public VSR datasets demonstrate the superiority of our method over other state-of-the-art methods in terms of both quantitative and qualitative metrics.

【 授权许可】

Unknown