基于组反馈融合机制的视频超分辨率模型

视频超分辨率（video super-resolution，VSR）的目的是利用多个相邻帧的信息来生成参考帧的高分辨率版本。现有的许多VSR工作都集中在如何有效地对齐相邻帧以更好地融合相邻帧信息，而很少在相邻帧信息融合这一重要步骤上进行研究。针对该问题，提出了基于组反馈融合机制的视频超分辩模型（GFFMVSR）。具体来说，在相邻帧对齐后，将对齐视频序列输入第一重时间注意力模块；然后，将序列分成几个小组，各小组依次通过组内融合模块实现初步融合。不同小组的融合结果经过第二重时间注意力模块；然后，各小组逐组输入反馈融合模块，利用反馈机制反馈融合不同组别的信息，最后将融合结果输出重建。经验证，该模型具有较强的信息融合能力，在客观评价指标和主观视觉效果上都优于现有的模型。

Video super-resolution model based on group feedback fusion mechanism

Video super-resolution(VSR) aims to exploit information from multiple adjacent frames to generate a high-resolution version of a reference frame. Many existing VSR works focus on how to effectively align adjacent frames to better fuse adjacent frame information, and little research has been done on the important step of adjacent frame information fusion. To solve this problem, this paper proposed a video super-resolution model based on group feedback fusion mechanism(GFFMVSR). Specifically, after adjacent frames were aligned, it input the aligned video sequences to the first temporal attention module. Then, it divided the sequence into several groups, and each group achieved preliminary fusion through the intra-group fusion module in turn. Next, the fusion results of different groups went through a second temporal attention module. Then, each group input the feedback fusion module group by group, and used the feedback mechanism to feedback and fuse the information of different groups. Finally, it reconstructed the fusion result output. It verifies that the model has strong information fusion ability, and is superior to the existing models in both objective evaluation indicators and subjective visual effects.