论文标题
用于彩色图像插入的结构 - 汉克尔域中的生成建模
Generative Modeling in Structural-Hankel Domain for Color Image Inpainting
论文作者
论文摘要
近年来，一些研究人员专注于使用单个图像通过多尺度功能获得大量样品。这项研究旨在提出一个崭新的想法，该想法仅需要十个甚至更少的样本来构建基于彩色图像介入任务的基于得分的低级矩阵矩阵辅助生成模型（SHGM）。在先前的学习过程中，首先从几个图像中提取一定数量的内部中间斑块，然后从这些贴片中构建结构 - 汉氏矩阵。为了更好地应用基于分数的生成模型来学习斑块中的内部统计分布，大规模的Hankel矩阵最终被折叠到更高的维度张量中，以进行先进的学习。在迭代介绍过程中，SHGM将覆盖问题视为在低级别环境中的有条件生成过程。结果，通过执行随机微分方程求解器，乘数的交替方向方法以及数据一致性步骤来获得中间恢复的图像。实验结果证明了SHGM的出色性能和多样性。
In recent years, some researchers focused on using a single image to obtain a large number of samples through multi-scale features. This study intends to a brand-new idea that requires only ten or even fewer samples to construct the low-rank structural-Hankel matrices-assisted score-based generative model (SHGM) for color image inpainting task. During the prior learning process, a certain amount of internal-middle patches are firstly extracted from several images and then the structural-Hankel matrices are constructed from these patches. To better apply the score-based generative model to learn the internal statistical distribution within patches, the large-scale Hankel matrices are finally folded into the higher dimensional tensors for prior learning. During the iterative inpainting process, SHGM views the inpainting problem as a conditional generation procedure in low-rank environment. As a result, the intermediate restored image is acquired by alternatively performing the stochastic differential equation solver, alternating direction method of multipliers, and data consistency steps. Experimental results demonstrated the remarkable performance and diversity of SHGM.
