Knowledge Commons of Institute of Automation,CAS
Progressive polarization based reflection removal via realistic training data generation | |
Pang, Youxin1,2![]() ![]() ![]() | |
发表期刊 | PATTERN RECOGNITION
![]() |
ISSN | 0031-3203 |
2022-04-01 | |
卷号 | 124页码:13 |
摘要 | The reflection effect is unavoidable when taking photos through glasses or other transparent materials, which introduces undesired information into pictures. Hence, removing the influence of reflection becomes a key problem in computer vision. One of the main obstacles of recent learning based approaches is the lacking of realistic training data. To address this issue, we introduce a new dataset synthesis method as well as a novel neural network architecture for single image reflection removal. First, we make use of the polarization characteristics of light into the synthesis of datasets, so as to obtain more realistic and diversified training dataset POL. Then, we design a novel Progressive Polarization based Reflection Removal Network ((PR2)-R-2 Net), which preliminary estimates the coarse background layer to guide the final reflection removal. We demonstrate that our method performs better than the state-of-the-art single image reflection removal methods through quantitative and qualitative experimental comparisons. Specifically, the average PSNR of our restored images selected from three representative benchmark datesets: "Real20", "SIR2" and "Nature" is improved at least 0.49 compared with existing methods and reaches to 24.52. (C) 2021 Elsevier Ltd. All rights reserved. |
关键词 | Deep learning Reflection removal Polarization Progressive network Convolutional neural networks |
DOI | 10.1016/j.patcog.2021.108497 |
关键词[WOS] | SEPARATION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2019YFB2204104] ; National Natural Science Foundation of China[62102414] ; National Natural Science Foundation of China[62172415] ; National Natural Science Foundation of China[62071157] ; Alibaba Group through Alibaba Innovative Research Program |
项目资助者 | National Key R&D Program of China ; National Natural Science Foundation of China ; Alibaba Group through Alibaba Innovative Research Program |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000736972200008 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 模式识别基础 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47107 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Yuan, Mengke |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, PR, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.King Abdullah Univ Sci & Technol, Thuwal 239556900, Saudi Arabia 4.Alibaba Grp, 699 Wang Shang Rd, Hangzhou 310052, Zhejiang, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Pang, Youxin,Yuan, Mengke,Fu, Qiang,et al. Progressive polarization based reflection removal via realistic training data generation[J]. PATTERN RECOGNITION,2022,124:13. |
APA | Pang, Youxin,Yuan, Mengke,Fu, Qiang,Ren, Peiran,&Yan, Dong-Ming.(2022).Progressive polarization based reflection removal via realistic training data generation.PATTERN RECOGNITION,124,13. |
MLA | Pang, Youxin,et al."Progressive polarization based reflection removal via realistic training data generation".PATTERN RECOGNITION 124(2022):13. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Progressive polariza(4985KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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