LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

doi:10.1109/CVPRW59228.2023.00350

	LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results
	Sheng, Hao 1,2,3; Liu, Yebin 4; Yu, Jingyi5 ; Wu, Gaochang 6; Xiong, Wei 7; Guo, Longzhao 8; Xie, Yanlin 8; Zhang, Shuo 8; Chang, Song 8; Lin, Youfang 8; Chao, Wentao 9; Wang, Xuechun 9; Wang, Guanghui 10; Duan, Fuqing 9; Wang, Tun 1; Yang, Da 1,2; Cui, Zhenglong 1,2; Wang, Sizhe 1,2; Zhao, Mingyuan 1; Wang, Qiong 11; Chen, Qianyu 12; Liang, Zhengyu 12; Wang, Yingqian 12; Yang, Jungang 12; Yang, Xueting 13; Deng, Junli 13; Cong, Ruixuan 1,2; Chen, Rongshan 1,2
	2023
会议录名称	IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS
ISSN	2160-7508
卷号	2023-June
页码	3473-3485
发表状态	已发表
DOI	10.1109/CVPRW59228.2023.00350
摘要	This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research. © 2023 IEEE.
关键词	Data-source Depth Estimation Estimation methods Estimation results Evaluation phase Light fields Multi-view stereo Second phase Stereo-matching Two phase
会议名称	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
会议地点	Vancouver, BC, Canada
会议日期	June 18, 2023 - June 22, 2023
收录类别	EI
语种	英语
出版者	IEEE Computer Society
EI入藏号	20233714731199
EI主题词	Stereo image processing
EISSN	2160-7516
EI分类号	723.2 Data Processing and Image Processing
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348759
专题	信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Cong, Ruixuan; Chen, Rongshan
作者单位	1.State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China 2.Beihang Hangzhou Innovation Institute Yuhang, China 3.Faculty of Applied Sciences, Macao Polytechnic University, China 4.Tsinghua University, China 5.Shanghaitech University, China 6.State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China 7.Beijing Meet Yuan Co.,Ltd, China 8.Beijing Key Laboratory of Traffic Data Analysis and Mining, School of Computer and Information Technology, Beijing Jiaotong University, China 9.Beijing Normal University, China 10.Toronto Metropolitan University, Canada 11.College of Computer Science and Technology, Zhejiang University of Technology, China 12.National University of Defense Technology, China 13.School of Information and Communication Engineering, Communication University of China, China
推荐引用方式 GB/T 7714	Sheng, Hao,Liu, Yebin,Yu, Jingyi,et al. LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results[C]:IEEE Computer Society,2023:3473-3485.