Depth Estimation From Light Field Using Graph-Based Structure-Aware Analysis

被引:32
作者
Zhang, Yuchen [1 ]
Dai, Wenrui [2 ]
Xu, Mingxing [1 ]
Zou, Junni [2 ]
Zhang, Xiaopeng [3 ]
Xiong, Hongkai [1 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China
[3] Huawei Technol Co Ltd, Noahs Ark Lab, Shanghai 201206, Peoples R China
基金
中国国家自然科学基金;
关键词
Light field; depth map; graph spectral analysis; graph Laplacian matrix; FOURIER-TRANSFORM;
D O I
10.1109/TCSVT.2019.2954948
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Existing light field depth map estimation approaches only utilize partial angular views in occlusion areas and local spatial dependencies in the optimization. This paper proposes a novel two-stage light field depth estimation method via graph spectral analysis to exploit the complete correlations and dependencies within angular patches and spatial images. The initial depth map estimation leverages the undirected graph to jointly consider occluded and unoccluded views within each angular patch. The estimated depth minimizes the structural incoherence of its corresponding angular patch with the focused one by evaluating the highest graph frequency component. Subsequently, depth map refinement optimizes the initial depth map with the color consistency and smoothness formulated by weighted adjacency matrix. The structural constraints are efficiently employed using low-pass graph filtering with Chebyshev polynomial approximation. Experimental results demonstrate that the proposed method improves the depth map estimation, especially in the edge regions.
引用
收藏
页码:4269 / 4283
页数:15
相关论文
共 45 条
[1]   Graph Signal Recovery via Primal-Dual Algorithms for Total Variation Minimization [J].
Berger, Peter ;
Hannak, Gabor ;
Matz, Gerald .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2017, 11 (06) :842-855
[2]   The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution [J].
Bishop, Tom E. ;
Favaro, Paolo .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (05) :972-986
[3]   Light Field Stereo Matching Using Bilateral Statistics of Surface Cameras [J].
Chen, Can ;
Lin, Haiting ;
Yu, Zhan ;
Kang, Sing Bing ;
Yu, Jingyi .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :1518-1525
[4]   Light Field Compressed Sensing Over a Disparity-Aware Dictionary [J].
Chen, Jie ;
Chau, Lap-Pui .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 27 (04) :855-865
[5]  
Chen ML, 2015, ASIAPAC SIGN INFO PR, P1041, DOI 10.1109/APSIPA.2015.7415430
[6]  
Chen SH, 2014, 2014 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), P872, DOI 10.1109/GlobalSIP.2014.7032244
[7]   Benchmark Data Set and Method for Depth Estimation From Light Field Images [J].
Feng, Mingtao ;
Wang, Yaonan ;
Liu, Jian ;
Zhang, Liang ;
Zaki, Hasan F. M. ;
Mian, Ajmal .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (07) :3586-3598
[8]  
Gadde A, 2013, IEEE IMAGE PROC, P1222, DOI 10.1109/ICIP.2013.6738252
[9]   Reducing Plenoptic Camera Artifacts [J].
Georgiev, T. ;
Lumsdaine, A. .
COMPUTER GRAPHICS FORUM, 2010, 29 (06) :1955-1968
[10]  
Heber Stefan, 2014, Computer Vision - ECCV 2014. 13th European Conference. Proceedings: LNCS 8694, P751, DOI 10.1007/978-3-319-10599-4_48