基于块和低秩张量恢复的视频去噪方法

由于采用矩阵的表示形式会破坏视频数据的原始空间结构，针对这一问题，提出了一种基于块和低秩张量恢复的视频去噪方法。首先运用自适应中值滤波器对含噪视频进行预处理，通过相似块匹配构造一个三阶张量，根据视频张量的低秩性和噪声像素的稀疏性，利用基于张量的增广拉格朗日乘子法（ALM）重建出三阶视频张量的低秩部分和稀疏部分，实现噪声的分离。该方法采用张量模型来处理视频去噪的问题，更好地保护了视频序列的高维结构特性，可以准确地去除复杂结构视频的噪声干扰。实验结果表明，相对于常用方法，该方法能准确完整地分离噪声，具有更强的视频去噪能力。

Patch-based video denoising using low-rank tensor recovery

Since matrix representation of video data could damage its initial structure, this paper proposed a patch-based denoising method based on low-rank tensor recovery. Frist, a three order tensor was constructed through clustering similar patches in the preprocessing video sequences. Then according to low-rank property of video tensor and sparsity of noise artifacts, the proposed approach used the augmented Lagrange multipliers (ALM) to reconstruct the low-rank and sparse sensors, which could completely separate noise from the video tensor. This paper developed a tensor model to preserve the spatial structure of the video modality, thus it could remove the noise artifacts from complex video better. Simulation experiments show that this algorithm has the stronger ability of video denoising comparing with traditional methods.