Video Super-resolution via Hierarchical Feature Reuse
The performance improvement of current deep convolution neural network methods in video super-resol-ution task is slightly lower than that in image super-resolution task,partly because they do not make full use of some key inter-frame information in hierarchical structure features.In this paper,we propose hierarchical feature re-use network(HFRNet)to solve the problem mentioned above.The network retains the low-frequency content of the motion compensation frame,and use dense hierarchical feature block(DHFB)to adaptively fuse the features of each residual block within it,then long-term feature reuse is proposed to fuse the features between multiple dense hier-archical feature block,so as to promote the recovery of high-frequency detail information.Experimental results show that the proposed method is superior to the current method in both quantitative and qualitative metrics.
万方数据
维普
