arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09704cs.CV
收藏

移动自组网:利用多对齐网络改进视频去噪

MANet: Improving Video Denoising with a Multi-Alignment Network

The University of Hong Kong(香港大学);University of Rochester(罗切斯特大学);ACCESS –- AI Chip Center for Emerging Smart Systems(ACCESS——新兴智能系统人工智能芯片中心)

Yaping Zhao, Haitian Zheng, Zhongrui Wang, Jiebo Luo, Edmund Y. Lam

摘要:

在视频去噪中,相邻帧通常提供非常有用的信息,但在利用这些信息之前需要精确对齐。在这项工作中,我们提出了一个多对齐网络,它产生多个流的建议,然后基于注意力的平均。它用于模拟非局部机制,通过平均多个观测值来抑制噪声。我们的方法可以应用于各种国家的最先进的模型,是基于流量估计。在大规模视频数据集上的实验表明,该方法使去噪基线模型提高了0.2dB,并通过模型蒸馏进一步减少了47%的参数。代码可在https://github.com/IndigoPurple/MANet上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑