Image Inpainting Using Structure-Guided Priority Belief Propagation and Label Transformations

Heng-Feng Hsin,Jin-Jang Leou,Cheng-Shian Lin,Hsuan-Ying Chen

Pattern Recognition（2010）

引用 8|浏览0

暂无评分

摘要

In this study, an image in painting approach using structure-guided priority belief propagation (BP) and label transformations is proposed. The proposed approach contains five stages, namely, Markov random field (MRF) node determination, structure map generation, label set enlargement by label transformations, image in painting by priority-BP optimization, and overlapped region composition. Based on experimental results obtained in this study, as compared with three comparison approaches, the proposed approach provides the better image in painting results.

查看译文

关键词

optimisation,belief networks,comparison approach,painting result,belief propagation,random processes,image inpainting,structure map generation,label transformations,better image,label transformation,image restoration,struture map generation,markov random field,painting approach,markov random field node determination,priority-bp optimization,overlapped region composition,markov processes,mrf,node determination,structure-guided priority belief propagation,label set enlargement,lattices,optimization,message passing,pixel

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要