Stacked dense networks for single-image snow removal

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Stacked dense networks for single-image snow removal
	Tian JD(田建东)3,4 ; Li PY(李鹏越)3,4,5; Wu CD(吴成东)5; Wang GL(王国霖)2,3,4; Tang YD(唐延东)3,4 ; Yun, Mengshen 1
刊名	Neurocomputing
	2019
卷号	367 期号:20 页码:152-163
关键词	Snow removal Single image Stacked dense networks Image restoration
ISSN号	0925-2312
产权排序	1
英文摘要	Single image snow removal is important since snowy images usually degrade the performance of computer vision systems. In this paper, we deduce a physics-based snow model and propose a novel snow removal method based on the snow model and deep neural networks. Our model decomposes a snowy image into a nonlinear combination of a snow-free image and dynamic snowflakes. Inspired by our model and DenseNet connectivity pattern, we design a novel Multi-scale Stacked Densely Connected Convolutional Network (MS-SDN) to simultaneously detect and remove snowflakes in an image. The MS-SDN is composed of a multi-scale convolutional sub-net for extracting feature maps and two stacked modified DenseNets for snowflakes detection and removal. The snowflake detection sub-net guides snow removal through forward transmission, and the snowflake removal sub-net adjusts snow detection through back transmission. In this way, snowflake detection and removal mutually improve the final results. For training and testing our method, we constructed a large-scale benchmark synthesis dataset which contains 3000 triplets of snowy images, snowflakes, and snow-free images. Specifically, the snow-free images are captured from snow scenes, and the snowy images are synthesized by using our deduced snow model. Our extensive quantitative and qualitative experimental results show that our MS-SDN performs better than several state-of-the-art methods, and the stacked structure is better than multi-branch structures in terms of snow removal.
语种	英语
WOS记录号	WOS:000489017500015
资助机构	Natural Science Foundation of China under Grants no. 91648118 and 61821005 ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/25473]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Tian JD(田建东)
作者单位	1.College of Engineering, University of Illinois at Urbana-Champaign, Urbana, United States 2.University of Chinese Academy of Sciences, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, China 4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China 5.Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China
推荐引用方式 GB/T 7714	Tian JD,Li PY,Wu CD,et al. Stacked dense networks for single-image snow removal[J]. Neurocomputing,2019,367(20):152-163.
APA	Tian JD,Li PY,Wu CD,Wang GL,Tang YD,&Yun, Mengshen.(2019).Stacked dense networks for single-image snow removal.Neurocomputing,367(20),152-163.
MLA	Tian JD,et al."Stacked dense networks for single-image snow removal".Neurocomputing 367.20(2019):152-163.