Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction

doi:10.3390/s20061560

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction
	Chen, Ruijin 1,2; Gao, Wei 1,2
刊名	SENSORS
	2020-03-01
卷号	20 期号:6 页码:16
关键词	depth map super-resolution guidance residual network channel interaction
DOI	10.3390/s20061560
通讯作者	Gao, Wei(wgao@nlpr.ia.ac.cn)
英文摘要	We designed an end-to-end dual-branch residual network architecture that inputs a low-resolution (LR) depth map and a corresponding high-resolution (HR) color image separately into the two branches, and outputs an HR depth map through a multi-scale, channel-wise feature extraction, interaction, and upsampling. Each branch of this network contains several residual levels at different scales, and each level comprises multiple residual groups composed of several residual blocks. A short-skip connection in every residual block and a long-skip connection in each residual group or level allow for low-frequency information to be bypassed while the main network focuses on learning high-frequency information. High-frequency information learned by each residual block in the color image branch is input into the corresponding residual block in the depth map branch, and this kind of channel-wise feature supplement and fusion can not only help the depth map branch to alleviate blur in details like edges, but also introduce some depth artifacts to feature maps. To avoid the above introduced artifacts, the channel interaction fuses the feature maps using weights referring to the channel attention mechanism. The parallel multi-scale network architecture with channel interaction for feature guidance is the main contribution of our work and experiments show that our proposed method had a better performance in terms of accuracy compared with other methods.
资助项目	National Key R&D Program of China[2016YFB0502002] ; National Natural Science Foundation of China (NSFC)[61872361] ; National Natural Science Foundation of China (NSFC)[61991423] ; National Natural Science Foundation of China (NSFC)[61421004]
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
语种	英语
出版者	MDPI
WOS记录号	WOS:000529139700019
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/39399]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者	Gao, Wei
作者单位	1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Chen, Ruijin,Gao, Wei. Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction[J]. SENSORS,2020,20(6):16.
APA	Chen, Ruijin,&Gao, Wei.(2020).Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction.SENSORS,20(6),16.
MLA	Chen, Ruijin,et al."Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction".SENSORS 20.6(2020):16.