基于自动结构延伸的图像修补方法

Image Completion Based on Automatic Structure Propagation

针对图像修补问题中结构信息修补的难题,提出一种自动延伸图像中显著结构信息并完成图像修补的方法,通过提取图像未知区域周围的显著结构信息,并依据结构信息的趋势向未知区域中自动延伸,形成指导修补的辅助线,沿着辅助线修补显著结构信息后再利用基于块的纹理合成修复余下的未知区域,实验结果证明本文提出方法相比传统基于块的纹理合成方法能够得到更好的修补效果。

In order to resolve the challenging problem of repairing structure in image completion, we introduce a novel image completion approach based on automatic salient structure propagation. Our approach automatically finds the salient structural information around the unknown regions, and extends them into unknown regions to construct assistant curves. After synthesizing the missing structural information along the assistant curves, we fill in the remaining unknown regions using patch-based texture synthesis. Experiment results demonstrate a better effect of the proposed approach than that of the previous patch-based texture synthesis image completion method.