Generalized Random Walks for Fusion of Multi-Exposure Images

被引:189
作者
Shen, Rui [1 ]
Cheng, Irene [1 ]
Shi, Jianbo [2 ]
Basu, Anup [1 ]
机构
[1] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2E8, Canada
[2] Univ Penn, Dept Comp & Informat Sci, Philadelphia, PA 19104 USA
关键词
Image enhancement; image fusion; multi-exposure fusion; random walks; TONE REPRODUCTION; ALGORITHM;
D O I
10.1109/TIP.2011.2150235
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A single captured image of a real-world scene is usually insufficient to reveal all the details due to under-or over-exposed regions. To solve this problem, images of the same scene can be first captured under different exposure settings and then combined into a single image using image fusion techniques. In this paper, we propose a novel probabilistic model-based fusion technique for multi-exposure images. Unlike previous multi-exposure fusion methods, our method aims to achieve an optimal balance between two quality measures, i.e., local contrast and color consistency, while combining the scene details revealed under different exposures. A generalized random walks framework is proposed to calculate a globally optimal solution subject to the two quality measures by formulating the fusion problem as probability estimation. Experiments demonstrate that our algorithm generates high-quality images at low computational cost. Comparisons with a number of other techniques show that our method generates better results in most cases.
引用
收藏
页码:3634 / 3646
页数:13
相关论文
共 39 条
[1]  
Aggarwal M, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P2, DOI 10.1109/ICCV.2001.937492
[2]  
[Anonymous], 1984, Random walks and electric networks
[3]   Pattern-selective color image fusion [J].
Bogoni, L ;
Hansen, M .
PATTERN RECOGNITION, 2001, 34 (08) :1515-1526
[4]   Evaluation of HDR tone mapping methods using essential perceptual attributes [J].
Cadik, Martin ;
Wimmer, Michael ;
Neumann, Laszlo ;
Artusi, Alessandro .
COMPUTERS & GRAPHICS-UK, 2008, 32 (03) :330-349
[5]   Algorithm 887: CHOLMOD, Supernodal Sparse Cholesky Factorization and Update/Downdate [J].
Chen, Yanqing ;
Davis, Timothy A. ;
Hager, William W. ;
Rajamanickam, Sivasankaran .
ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2008, 35 (03)
[6]  
Cheng I., 2007, OMNIVIS '07: Proceedings of ICCV Workshop on Omnidirectional Vision, Camera Networks and Nonclassical Cameras, P1
[7]   Extending dynamic range of two color images under different exposures [J].
Cho, WH ;
Hong, KS .
PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, 2004, :853-856
[8]  
Debevec P. E., 1997, Computer Graphics Proceedings, SIGGRAPH 97, P369, DOI 10.1145/258734.258884
[9]   Adaptive logarithmic mapping for displaying high contrast scenes [J].
Drago, F ;
Myszkowski, K ;
Annen, T ;
Chiba, N .
COMPUTER GRAPHICS FORUM, 2003, 22 (03) :419-426
[10]   The transducer model for contrast detection and discrimination:: formal relations, implications, and an empirical test [J].
Garcia-Perez, Miguel A. ;
Alcala-Quintana, Rocio .
SPATIAL VISION, 2007, 20 (1-2) :5-43