Single image dehazing

被引:2109
作者
Fattal, Raanan [1 ]
机构
[1] Hebrew Univ Jerusalem, IL-91905 Jerusalem, Israel
来源
ACM TRANSACTIONS ON GRAPHICS | 2008年 / 27卷 / 03期
关键词
image dehazing/defogging; computational photography; image restoration; image enhancement; Markov random field image modeling;
D O I
10.1145/1360612.1360671
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper we present a new method for estimating the optical transmission in hazy scenes given a single input image. Based on this estimation, the scattered light is eliminated to increase scene visibility and recover haze-free scene contrasts. In this new approach we formulate a refined image formation model that accounts for surface shading in addition to the transmission function. This allows us to resolve ambiguities in the data by searching for a solution in which the resulting shading and transmission functions are locally statistically uncorrelated. A similar principle is used to estimate the color of the haze. Results demonstrate the new method abilities to remove the haze layer as well as provide a reliable transmission estimate which can be used for additional applications such as image refocusing and novel view synthesis.
引用
收藏
页数:9
相关论文
共 32 条
[1]  
Andrews D.F., 1972, ROBUST ESTIMATES LOC
[2]  
[Anonymous], P CVPR
[3]  
[Anonymous], ACM SIGGRAPH
[4]  
[Anonymous], 2006, P COMP VIS PATT REC
[6]  
Coon D., 2005, PSYCHOL MODULAR APPR
[7]   Haze detection and removal in high resolution satellite image with wavelet analysis [J].
Du, Y ;
Guindon, B ;
Cihlar, J .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (01) :210-217
[8]  
Fattal R, 2007, ACM T GRAPHIC, V26, DOI 10.1145/1276377.1276441
[9]  
Fattal R, 2007, ACM T GRAPHIC, V26, DOI 10.1145/1276377.1276496
[10]   Atmospheric attenuation reduction through multi-sensor fusion [J].
Grewe, L ;
Brooks, RR .
SENSOR FUSION: ARCHITECTURES, ALGORITHMS, AND APPLICATIONS II, 1998, 3376 :102-109