论文标题
MANET：通过多对准网络改进视频Denoising
MANet: Improving Video Denoising with a Multi-Alignment Network
论文作者
论文摘要
在视频deNoising中，相邻的框架通常提供非常有用的信息，但是需要准确的对齐方式，然后才能刺激此类信息。在这项工作中，我们提出了一个多对准网络，该网络生成了多个流动建议，然后是基于注意的平均。它可以模仿非本地机制，通过平均多个观测来抑制噪声。我们的方法可以应用于基于流量估计的各种最新模型。大规模视频数据集上的实验表明，我们的方法通过0.2DB提高了denoisis的基线模型，并通过模型蒸馏进一步将参数降低了47％。代码可在https://github.com/indigopurple/manet上找到。
In video denoising, the adjacent frames often provide very useful information, but accurate alignment is needed before such information can be harnassed. In this work, we present a multi-alignment network, which generates multiple flow proposals followed by attention-based averaging. It serves to mimic the non-local mechanism, suppressing noise by averaging multiple observations. Our approach can be applied to various state-of-the-art models that are based on flow estimation. Experiments on a large-scale video dataset demonstrate that our method improves the denoising baseline model by 0.2dB, and further reduces the parameters by 47% with model distillation. Code is available at https://github.com/IndigoPurple/MANet.
