论文标题
视频超分辨率的可变形3D卷积
Deformable 3D Convolution for Video Super-Resolution
论文作者
论文摘要
视频序列之间的时空信息对于视频超分辨率（SR）很重要。但是，现有视频SR方法无法完全使用时空信息，因为通常会顺序执行空间特征提取和时间运动补偿。在本文中，我们提出了一个可变形的3D卷积网络（D3DNET），以合并来自视频SR的时空和时间维度的时空信息。具体而言，我们引入了可变形的3D卷积（D3D），以将变形卷积与3D卷积整合，从而获得了上空时空的建模能力和运动感知的建模灵活性。广泛的实验证明了D3D在利用时空信息中的有效性。比较结果表明，我们的网络实现了最先进的SR性能。代码可在以下网址提供：https：//github.com/xinyiying/d3dnet。
The spatio-temporal information among video sequences is significant for video super-resolution (SR). However, the spatio-temporal information cannot be fully used by existing video SR methods since spatial feature extraction and temporal motion compensation are usually performed sequentially. In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR. Specifically, we introduce deformable 3D convolution (D3D) to integrate deformable convolution with 3D convolution, obtaining both superior spatio-temporal modeling capability and motion-aware modeling flexibility. Extensive experiments have demonstrated the effectiveness of D3D in exploiting spatio-temporal information. Comparative results show that our network achieves state-of-the-art SR performance. Code is available at: https://github.com/XinyiYing/D3Dnet.
