Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising
Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising
复制标题
DOI：
10.1109/lgrs.2022.3192912
复制
发表时间：
2022-07
影响因子：
4.8
通讯作者：
Shingo Takemoto;Kazuki Naganuma;Shunsuke Ono
中科院分区：
文献类型：
--
作者：
Shingo Takemoto;Kazuki Naganuma;Shunsuke Ono
空间-光谱全变分（SSTV）模型作为一种有效的高光谱图像正则化方法被广泛应用于混合噪声去除等各种应用。然而，由于SSTV对局部空间差异的计算是均匀的，因此很难在保留具有精细边缘和纹理的复杂空间结构的情况下去除噪声，特别是在高噪声强度的情况下。为了解决这一问题，我们提出了一种新的tv型正则化算法，称为图- sstv (GSSTV)，它从有噪声的HSI中生成一个明确反映目标HSI空间结构的图，并结合基于该图设计的加权空间差分算子。在此基础上，我们将混合噪声去除问题归结为一个包含GSSTV的凸优化问题，并开发了一种基于原对偶分裂方法的高效算法来解决该问题。最后，通过混合噪声去除实验，对比了GSSTV与现有HSI正则化模型的有效性。源代码可从https://www.mdi.c.titech.ac.jp/publications/gsstv获得。
The spatio-spectral total variation (SSTV) model has been widely used as an effective regularization of hyperspectral images (HSIs) for various applications such as mixed noise removal. However, since SSTV computes local spatial differences uniformly, it is difficult to remove noise while preserving complex spatial structures with fine edges and textures, especially in situations of high noise intensity. To solve this problem, we propose a new TV-type regularization called graph-SSTV (GSSTV), which generates a graph explicitly reflecting the spatial structure of the target HSI from noisy HSIs and incorporates a weighted spatial difference operator designed based on this graph. Furthermore, we formulate the mixed noise removal problem as a convex optimization problem involving GSSTV and develop an efficient algorithm based on the primal-dual splitting method to solve this problem. Finally, we demonstrate the effectiveness of GSSTV compared with existing HSI regularization models through experiments on mixed noise removal. The source code will be available at https://www.mdi.c.titech.ac.jp/publications/gsstv.