Exemplar-based image inpainting using structure consistent patch matching
Exemplar-based image inpainting using structure consistent patch matching
复制标题
使用结构一致的补丁匹配进行基于示例的图像修复
DOI：
10.1016/j.neucom.2016.08.149
复制
发表时间：
2017-12
期刊：
影响因子：
6
通讯作者：
Li Xiao Xin
中科院分区：
文献类型：
--
作者：
Wang Haixia;Jiang Li;Liang Ronghua;Li Xiao Xin
图像修复是根据图像中已知区域的信息，对图像中丢失或劣化的部分进行修复。Criminisi提出了一种有效的基于样本的修复方法，该方法兼具纹理合成和基于扩散的修复的优点。然而，它也有自己的缺点，即优先级下降快和视觉不一致。本文提出了一种空间变化的置信项更新策略和一种匹配置信项，以改进填充优先级估计。我们提出了结构一致的补丁匹配考虑到源和目标补丁差异的分布。采用快速傅里叶变换进行全图像搜索，以达到更好、更快的匹配效果。实验结果证明了我们提出的方法所取得的改进。
Image inpainting restores lost or deteriorated parts of images according to the information of known regions. Criminisi has proposed an effective exemplar-based inpainting method, which has the advantages of both texture synthesis and diffusion-based inpainting. Yet, it has its own flaws of fast priority dropping and visual inconsistency. In this paper, we propose a space varying updating strategy for the confidence term and a matching confidence term to improve the filling priority estimation. We propose structure consistent patch matching to take the distribution of source and target patch differences into account. Fast Fourier transform is adapted for full image searching to achieve better and faster matching results. Experimental results are given to demonstrate the improvements made by our proposed method.