论文标题
动态场景视频使用非本地关注
Dynamic Scene Video Deblurring using Non-Local Attention
论文作者
论文摘要
本文解决了视频浮肿的具有挑战性的问题。大多数现有作品都取决于时间信息融合的隐式或明确的一致性，这会增加计算成本或由于错误对准而导致次优性能。在这项研究中，我们提出了一个分解的时空注意力，以跨空间和时间进行非本地操作，以充分利用可用信息而不依赖于对齐。与现有的融合技术相比，它表现出较高的性能，同时又高效。多个数据集上的广泛实验证明了我们方法的优势。
This paper tackles the challenging problem of video deblurring. Most of the existing works depend on implicit or explicit alignment for temporal information fusion which either increase the computational cost or result in suboptimal performance due to wrong alignment. In this study, we propose a factorized spatio-temporal attention to perform non-local operations across space and time to fully utilize the available information without depending on alignment. It shows superior performance compared to existing fusion techniques while being much efficient. Extensive experiments on multiple datasets demonstrate the superiority of our method.
