Joint Bi-layer Optimization for Single-image Rain Streak Removal
文献类型：会议论文
| 作者 | Lei Zhu; Chi-Wing Fu; Dani Lischinski; Pheng-Ann Heng |
| 出版日期 | 2017 |
| 会议地点 | 意大利威尼斯 |
| 英文摘要 | We present a novel method for removing rain streaks from a single input image by decomposing it into a rain-free back- ground layer B and a rain-streak layer R. A joint opti- mization process is used that alternates between removing rain-streak details from B and removing non-streak details from R. The process is assisted by three novel image pri- ors. Observing that rain streaks typically span a narrow range of directions, we first analyze the local gradient s- tatistics in the rain image to identify image regions that are dominated by rain streaks. From these regions, we estimate the dominant rain streak direction and extract a collection of rain-dominated patches. Next, we define two priors on the background layer B, one based on a centralized sparse representation and another based on the estimated rain di- rection. A third prior is defined on the rain-streak layer R, based on similarity of patches to the extracted rain patches. Both visual and quantitative comparisons demonstrate that our method outperforms the state-of-the-art. |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/11807]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2017 |
| 推荐引用方式 GB/T 7714 | Lei Zhu,Chi-Wing Fu,Dani Lischinski,et al. Joint Bi-layer Optimization for Single-image Rain Streak Removal[C]. 见:. 意大利威尼斯. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。