Li Dingyi, Liu Yu, Wang Zengfu
IEEE Trans Image Process. 2018 Oct 22. doi: 10.1109/TIP.2018.2877334.
Video super-resolution (SR) aims at restoring fine details and enhancing visual experience for low-resolution (LR) videos. In this paper, we propose a very deep non-simultaneous fully recurrent convolutional network for video SR. To make full use of temporal information, we employ motion compensation, very deep fully recurrent convolutional layers and late fusion in our system. Residual connection is also employed in our recurrent structure for more accurate SR. Finally a new model ensemble strategy is used to combine our method with single-image SR method. Experimental results demonstrate that the proposed method is better than state-of-the-art SR methods on quantitative visual quality assessment.
视频超分辨率（SR）旨在为低分辨率（LR）视频恢复精细细节并提升视觉体验。在本文中，我们提出了一种用于视频SR的非常深的非同步全循环卷积网络。为了充分利用时间信息，我们在系统中采用了运动补偿、非常深的全循环卷积层和后期融合。我们的循环结构中还采用了残差连接以实现更精确的SR。最后，使用一种新的模型集成策略将我们的方法与单图像SR方法相结合。实验结果表明，在定量视觉质量评估方面，所提出的方法优于当前最先进的SR方法。
