WAVELET INPAINTING BY NONLOCAL TOTAL VARIATION
WAVELET INPAINTING BY NONLOCAL TOTAL VARIATION
复制标题
DOI：
10.3934/ipi.2010.4.191
复制
发表时间：
2010-02
影响因子：
1.3
通讯作者：
Xiaoqun Zhang;T. Chan
中科院分区：
文献类型：
--
作者：
Xiaoqun Zhang;T. Chan
小波修复问题包括填充小波域中丢失的数据。在[17]中，Chan、Shen 和 Zhou 提出了一种通过结合全变分正则化和小波表示来恢复分段恒定或平滑图像的有效方法。在本文中，我们将其扩展到非局部全变分正则化，以便同时恢复纹理和局部几何结构。此外，我们为局部和非局部正则化器应用了有效的算法框架。对各种丢失场景和自然图像的大量实验结果验证了该方法的性能。
Wavelet inpainting problem consists of filling in missed data in the wavelet domain. In [17], Chan, Shen, and Zhou proposed an efficient method to recover piecewise constant or smooth images by combining total variation regularization and wavelet representations. In this paper, we extend it to nonlocal total variation regularization in order to recover textures and local geometry structures simultaneously. Moreover, we apply an efficient algorithm framework for both local and nonlocal regularizers. Extensive experimental results on a variety of loss scenarios and natural images validate the performance of this approach.