Learning across views for stereo image completion

doi:10.1049/iet-cvi.2019.0775

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	Learning across views for stereo image completion
	Ma, Wei 1; Zheng, Mana 1; Ma, Wenguang 1; Xu, Shibiao2 ; Zhang, Xiaopeng2
发表期刊	IET COMPUTER VISION
ISSN	1751-9632
	2020-10-01
卷号	14 期号:7 页码:482-492
通讯作者	Xu, Shibiao(shibiao.xu@nlpr.ia.ac.cn)
摘要	Stereo image completion (SIC) is to fill holes existing in a pair of stereo images. SIC is more complicated than single image repairing, which needs to complete the pair of images while keeping their stereoscopic consistency. In recent years, deep learning has been introduced into single image repairing but seldom used for SIC. The authors present a novel deep learning-based approach for SIC. In their method, an X-shaped fully convolutional network (called SICNet) is proposed and designed to complete stereo images, which is composed of two branches of convolutional neural network layers to encode the context of the left and right images separately, a fusion module for stereo-interactive completion, and two branches of decoders to produce completed left and right images, respectively. In consideration of both inter-view and intra-view cues, they introduce auxiliary networks and define comprehensive losses to train SICNet to perform single-view coherent and cross-view consistent completion simultaneously. Extensive experiments are conducted to show the state-of-the-art performances of the proposed approach and its key components.
DOI	10.1049/iet-cvi.2019.0775
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000598689800009
出版者	INST ENGINEERING TECHNOLOGY-IET
七大方向——子方向分类	三维视觉
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42720
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	Xu, Shibiao
作者单位	1.Beijing Univ Technol, Fac Informat Technol, 100 Pingleyuan St, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
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	Ma, Wei,Zheng, Mana,Ma, Wenguang,et al. Learning across views for stereo image completion[J]. IET COMPUTER VISION,2020,14(7):482-492.
APA	Ma, Wei,Zheng, Mana,Ma, Wenguang,Xu, Shibiao,&Zhang, Xiaopeng.(2020).Learning across views for stereo image completion.IET COMPUTER VISION,14(7),482-492.
MLA	Ma, Wei,et al."Learning across views for stereo image completion".IET COMPUTER VISION 14.7(2020):482-492.