APAN: Across-Scale Progressive Attention Network for Single Image Deraining
文献类型:期刊论文
作者 | Wang Q(王强)1,2; Sun G(孙干)1,3; Fan HJ(范慧杰)1,3; Li WT(李文涛)1,3; Tang YD(唐延东)1,3 |
刊名 | IEEE SIGNAL PROCESSING LETTERS |
出版日期 | 2022 |
卷号 | 29页码:159-163 |
ISSN号 | 1070-9908 |
关键词 | Rain Image reconstruction Training Feature extraction Convolutional neural networks Sun Predictive models Across-scale attention networks feature representation image deraing |
产权排序 | 1 |
英文摘要 | Recent single image deraining works have achieved significant improvement using convolutional neural networks. However, the rain streaks in the rain image share similar patterns with its multi-scale versions, which are not fully exploited in recent works. In this paper, we propose an Across-scale Progressive Attention Network (i.e., APAN) to explore the multi-scale collaborative representation for single image deraining. Specifically, we represent each rainy image via a multi-scale module. An across-scale attention module is then used to capture long-range feature correspondences from multi-scale features, which can model the rain streaks at an enlarging feature dimension. Afterwards, we construct a pyramid structure and further predict the rain streak progressively, which also guides the across-scale attention module to refine the feature representation from coarse to fine. The proposed model exploits self-similarity of features via an across-scale attention between different scales, which can well model the rain streak with long-range information. Experiments on several datasets show that our model achieves significant improvement compared with most state-of-the-art deraining models. |
WOS关键词 | RAIN STREAKS REMOVAL ; MODEL |
资助项目 | National Natural Science Foundation of China[62073205] ; National Natural Science Foundation of China[61991413] ; National Natural Science Foundation of China[62003336] ; National Natural Science Foundation of China[61903358] ; Liaoning Key Research and Development Program[2019JH2/10300014] |
WOS研究方向 | Engineering |
语种 | 英语 |
WOS记录号 | WOS:000747445300013 |
资助机构 | National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [62073205, 61991413, 62003336, 61903358] ; Liaoning Key Research and Development Program [2019JH2/10300014] |
源URL | [http://ir.sia.cn/handle/173321/30311] |
专题 | 沈阳自动化研究所_机器人学研究室 |
通讯作者 | Sun G(孙干) |
作者单位 | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.Key Laboratory of Manufacturing Industrial Integrated, Shenyang University, Shenyang 110000, Liaoning, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China |
推荐引用方式 GB/T 7714 | Wang Q,Sun G,Fan HJ,et al. APAN: Across-Scale Progressive Attention Network for Single Image Deraining[J]. IEEE SIGNAL PROCESSING LETTERS,2022,29:159-163. |
APA | Wang Q,Sun G,Fan HJ,Li WT,&Tang YD.(2022).APAN: Across-Scale Progressive Attention Network for Single Image Deraining.IEEE SIGNAL PROCESSING LETTERS,29,159-163. |
MLA | Wang Q,et al."APAN: Across-Scale Progressive Attention Network for Single Image Deraining".IEEE SIGNAL PROCESSING LETTERS 29(2022):159-163. |
入库方式: OAI收割
来源:沈阳自动化研究所
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。