STRUCTURE-GUIDED IMAGE COMPLETION VIA REGULARITY STATISTICS | |
Yang, Shuai ; Liu, Jiaying ; Song, Sijie ; Li, Mading ; Guo, Zongming | |
2016 | |
关键词 | Image completion structure detection perspective transformation image inpainting |
英文摘要 | In this paper, we propose a novel hierarchical image completion approach using regularity statistics, considering structure features. Guided by dominant structures, the target image is used to generate reference images in a self-reproductive way by image data enhancement. The structure-guided image data enhancement allows us to expand the search space for samples. A Markov Random Field model is used to guide the enhanced image data combination to globally reconstruct the target image. For lower computational complexity and more accurate structure estimation, a hierarchical process is implemented. Experiments demonstrate the effectiveness of our method comparing to several state-of-the-art image completion techniques.; CPCI-S(ISTP); 1711-1715 |
语种 | 英语 |
出处 | IEEE International Conference on Acoustics, Speech, and Signal Processing |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/459992] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Yang, Shuai,Liu, Jiaying,Song, Sijie,et al. STRUCTURE-GUIDED IMAGE COMPLETION VIA REGULARITY STATISTICS. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论