arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.02504cs.CV
收藏

从秩估计到秩逼近:秩残差约束在图像复原中的应用

From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration

University of Electronic Science and Technology of China(电子科技大学);Nokia Bell Labs(诺基亚贝尔实验室);Nanyang Technological University(南洋理工大学);University of Macau(澳门大学);Nanjing Institute of Technology(南京工程学院)

Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou, Jiachao Zhang, Ce Zhu

摘要:

在本文中,我们提出了一种新的方法来秩最小化问题,称为秩剩余约束(RRC)模型。不同于现有的基于低秩的方法,如著名的核范数最小化(NNM)和加权核范数最小化(WNNM),估计底层的低秩矩阵直接从损坏的观察,我们逐步逼近底层的低秩矩阵通过最小化秩残差。通过将图像非局部自相似性(NSS)先验知识与RRC模型相结合,将其应用于图像复原任务中,包括图像去噪和图像压缩伪影抑制。为此,我们首先获得一个良好的参考原始图像组通过使用图像NSS先验,然后之间的参考和退化图像的图像组的秩残差最小化,以实现更好的估计到所需的图像。以这种方式,参考图像和估计图像在每次迭代中逐渐地并且联合地更新。在基于组的稀疏表示模型的基础上,我们进一步对所提出的RRC模型的可行性进行了理论分析。实验结果表明,所提出的RRC模型优于许多国家的最先进的方案在客观和感知质量。

英文摘要:

In this paper, we propose a novel approach to the rank minimization problem, termed rank residual constraint (RRC) model. Different from existing low-rank based approaches, such as the well-known nuclear norm minimization (NNM) and the weighted nuclear norm minimization (WNNM), which estimate the underlying low-rank matrix directly from the corrupted observations, we progressively approximate the underlying low-rank matrix via minimizing the rank residual. Through integrating the image nonlocal self-similarity (NSS) prior with the proposed RRC model, we apply it to image restoration tasks, including image denoising and image compression artifacts reduction. Towards this end, we first obtain a good reference of the original image groups by using the image NSS prior, and then the rank residual of the image groups between this reference and the degraded image is minimized to achieve a better estimate to the desired image. In this manner, both the reference and the estimated image are updated gradually and jointly in each iteration. Based on the group-based sparse representation model, we further provide a theoretical analysis on the feasibility of the proposed RRC model. Experimental results demonstrate that the proposed RRC model outperforms many state-of-the-art schemes in both the objective and perceptual quality.

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。

↑