论文标题
带有复发结构网络的视频超分辨率
Video Super-Resolution with Recurrent Structure-Detail Network
论文作者
论文摘要
大多数视频超分辨率方法在时间滑动窗口中的相邻帧有助于超级溶解单个参考框架。与基于复发的方法相比，它们效率较低。在这项工作中，我们提出了一种新型的经常性视频超分辨率方法，该方法既有效又有效地利用先前的帧来超级溶解当前帧。它将输入分为结构和细节组件，这些组件被馈送到由几个提出的两流结构 - 详细块组成的复发单元。此外，允许当前框架可以选择性地使用隐藏状态信息的隐藏状态适应模块，以增强其对外观变化和误差积累的鲁棒性。广泛的消融研究验证了所提出的模块的有效性。几个基准数据集的实验证明了该方法的出色性能与视频超分辨率的最新方法相比。
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame. It divides the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks. In addition, a hidden state adaptation module that allows the current frame to selectively use information from hidden state is introduced to enhance its robustness to appearance change and error accumulation. Extensive ablation study validate the effectiveness of the proposed modules. Experiments on several benchmark datasets demonstrate the superior performance of the proposed method compared to state-of-the-art methods on video super-resolution.
