A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation

doi:10.3390/s22239483

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation
	Shen, Yu1,2 ; Liu, Yuhang 1,2; Tian, Yonglin 1; Liu, Zhongmin 3; Wang, Feiyue1,4,5
发表期刊	SENSORS
	2022-12-01
卷号	22 期号:23 页码:15
通讯作者	Wang, Feiyue(feiyue.wang@ia.ac.cn)
摘要	Computer vision tasks, such as motion estimation, depth estimation, object detection, etc., are better suited to light field images with more structural information than traditional 2D monocular images. However, since costly data acquisition instruments are difficult to calibrate, it is always hard to obtain real-world scene light field images. The majority of the datasets for static light field images now available are modest in size and cannot be used in methods such as transformer to fully leverage local and global correlations. Additionally, studies on dynamic situations, such as object tracking and motion estimates based on 4D light field images, have been rare, and we anticipate a superior performance. In this paper, we firstly propose a new static light field dataset that contains up to 50 scenes and takes 8 to 10 perspectives for each scene, with the ground truth including disparities, depths, surface normals, segmentations, and object poses. This dataset is larger scaled compared to current mainstream datasets for depth estimation refinement, and we focus on indoor and some outdoor scenarios. Second, to generate additional optical flow ground truth that indicates 3D motion of objects in addition to the ground truth obtained in static scenes in order to calculate more precise pixel level motion estimation, we released a light field scene flow dataset with dense 3D motion ground truth of pixels, and each scene has 150 frames. Thirdly, by utilizing the DistgDisp and DistgASR, which decouple the angular and spatial domain of the light field, we perform disparity estimation and angular super-resolution to evaluate the performance of our light field dataset. The performance and potential of our dataset in disparity estimation and angular super-resolution have been demonstrated by experimental results.
关键词	light field parallel intelligence disparity estimation scene flow digital twin virtual real interaction angular super-resolution
DOI	10.3390/s22239483
关键词[WOS]	GEOMETRY
收录类别	SCI
语种	英语
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000896415800001
出版者	MDPI
引用统计	被引频次：1[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/173211/50816
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Wang, Feiyue
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.North Automat Control Technol Inst, Taiyuan 030006, Peoples R China 4.Macau Univ Sci & Technol, Macao Inst Syst Engn, Macau 999078, Peoples R China 5.Chinese Acad Sci, Inst Automat, Beijing Engn Res Ctr Intelligent Syst & Technol, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shen, Yu,Liu, Yuhang,Tian, Yonglin,et al. A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation[J]. SENSORS,2022,22(23):15.
APA	Shen, Yu,Liu, Yuhang,Tian, Yonglin,Liu, Zhongmin,&Wang, Feiyue.(2022).A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation.SENSORS,22(23),15.
MLA	Shen, Yu,et al."A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation".SENSORS 22.23(2022):15.