Efficient Video Deblurring Guided by Motion Magnitude
Efficient Video Deblurring Guided by Motion Magnitude
复制标题
DOI：
10.48550/arxiv.2207.13374
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Yusheng Wang;Yunfan Lu;Ye Gao;Lin Wang;Zhihang Zhong;Yinqiang Zheng;Atsushi Yamashita
中科院分区：
文献类型：
--
作者：
Yusheng Wang;Yunfan Lu;Ye Gao;Lin Wang;Zhihang Zhong;Yinqiang Zheng;Atsushi Yamashita
． 视频去模糊是一个高度受限的问题，由于空间和时间变化的模糊。一种直观的视频去模糊方法包括两个步骤：a)检测当前帧中的模糊区域；B)利用相邻帧中清晰区域的信息进行当前帧去模糊。为了实现这个过程，我们的想法是检测每帧像素级的模糊水平，并将其与视频去模糊相结合。为此，我们提出了一种利用运动幅度先验（MMP）作为有效深度视频去模糊指导的新框架。具体来说，由于曝光时间内像素沿轨迹的运动与运动模糊水平呈正相关，我们首先使用高频锐帧的光流平均星等来生成合成模糊帧及其相应的逐像素运动星等图。然后我们构建一个包含模糊帧和MMP对的数据集。然后通过一个紧凑的CNN通过回归学习MMP。MMP包括空间和时间模糊水平信息，这些信息可以进一步集成到一个有效的递归神经网络（RNN）中用于视频去模糊。我们进行了大量的实验来验证所提出的方法在公共数据集上的有效性。我们的代码可在https://github.com/sollynoay/MMP-RNN上获得。
. Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current frame deblurring. To realize this process, our idea is to detect the pixel-wise blur level of each frame and combine it with video deblurring. To this end, we propose a novel framework that utilizes the motion magnitude prior (MMP) as guidance for efficient deep video deblurring. Specifically, as the pixel movement along its trajectory during the exposure time is positively correlated to the level of motion blur, we first use the average magnitude of optical flow from the high-frequency sharp frames to generate the synthetic blurry frames and their corresponding pixel-wise motion magnitude maps. We then build a dataset including the blurry frame and MMP pairs. The MMP is then learned by a compact CNN by regression. The MMP consists of both spatial and temporal blur level information, which can be further integrated into an efficient recurrent neural network (RNN) for video deblurring. We conduct intensive experiments to validate the effectiveness of the proposed methods on the public datasets. Our codes are available at https://github.com/sollynoay/MMP-RNN .