Information Prebuilt Recurrent Reconstruction Network for Video Super-Resolution
This work addresses a specific bottleneck in video super-resolution for applications requiring low latency, offering an incremental improvement over existing recurrent methods.
The authors tackled the problem of unbalanced temporal receptive fields in unidirectional recurrent networks for video super-resolution, which causes earlier frames to be blurry or artifacted, and proposed an information prebuilt recurrent reconstruction network (IPRRN) that integrates front video information to balance input differences, achieving better quantitative and qualitative performance compared to state-of-the-art methods.
The video super-resolution (VSR) method based on the recurrent convolutional network has strong temporal modeling capability for video sequences. However, the temporal receptive field of different recurrent units in the unidirectional recurrent network is unbalanced. Earlier reconstruction frames receive less spatio-temporal information, resulting in fuzziness or artifacts. Although the bidirectional recurrent network can alleviate this problem, it requires more memory space and fails to perform many tasks with low latency requirements. To solve the above problems, we propose an end-to-end information prebuilt recurrent reconstruction network (IPRRN), consisting of an information prebuilt network (IPNet) and a recurrent reconstruction network (RRNet). By integrating sufficient information from the front of the video to build the hidden state needed for the initially recurrent unit to help restore the earlier frames, the information prebuilt network balances the input information difference at different time steps. In addition, we demonstrate an efficient recurrent reconstruction network, which outperforms the existing unidirectional recurrent schemes in all aspects. Many experiments have verified the effectiveness of the network we propose, which can effectively achieve better quantitative and qualitative evaluation performance compared to the existing state-of-the-art methods.