论文标题
空间空间手工空间：通过循环项目相互学习的时空视频超分辨率
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
论文作者
论文摘要
时空视频超分辨率（ST-VSR）旨在生成具有较高分辨率（HR）和较高帧速率（HFR）的超级分辨视频。从直觉上讲，基于两阶段的方法通过直接结合两个子任务来完成ST-VSR：空间视频超分辨率（S-VSR）和时间视频超级分辨率（T-VSR），但忽略了它们之间的恋爱关系。具体而言，1）T-VSR到S-VSR：时间相关性有助于具有更多线索的准确空间细节表示； 2）S-VSR到T-VSR：丰富的空间信息有助于时间预测的完善。为此，我们提出了一个基于单阶段的循环投影相互学习网络（CYCMU-NET），用于ST-VSR，该网络通过S-VSR和T-VSR之间的相互学习充分利用时空相关性。具体而言，我们建议通过迭代上下的预测来利用它们之间的共同信息，在该预测中，空间和时间特征完全融合和蒸馏，有助于高质量的视频重建。除了在基准数据集上进行广泛的实验外，我们还将提出的CYCMU-NET与S-VSR和T-VSR任务进行了比较，这表明我们的方法显着优于最先进的方法。
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution(HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR by directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal Video Super-Resolution(T-VSR) but ignore the reciprocal relations among them. Specifically, 1) T-VSR to S-VSR: temporal correlations help accurate spatial detail representation with more clues; 2) S-VSR to T-VSR: abundant spatial information contributes to the refinement of temporal prediction. To this end, we propose a one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR, which makes full use of spatial-temporal correlations via the mutual learning between S-VSR and T-VSR. Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction. Besides extensive experiments on benchmark datasets, we also compare our proposed CycMu-Net with S-VSR and T-VSR tasks, demonstrating that our method significantly outperforms state-of-the-art methods.
