O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images

被引:494
作者
Ancuti, Codruta O. [1 ]
Ancuti, Cosmin [1 ]
Timofte, Radu [2 ,3 ]
De Vleeschouwer, Christophe [4 ]
机构
[1] Univ Politehn Timisoara, MEO, Timisoara, Romania
[2] Swiss Fed Inst Technol, Zurich, Switzerland
[3] Merantix GmbH, Berlin, Germany
[4] Catholic Univ Louvain, ICTEAM, Louvain, Belgium
来源
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2018年
关键词
D O I
10.1109/CVPRW.2018.00119
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years. Despite this growing interest, the scientific community is still lacking a reference dataset to evaluate objectively and quantitatively the performance of proposed dehazing methods. The few datasets that are currently considered, both for assessment and training of learning-based dehazing techniques, exclusively rely on synthetic hazy images. To address this limitation, we introduce the first outdoor scenes database (named O-HAZE) composed of pairs of real hazy and corresponding haze-free images. In practice, hazy images have been captured in presence of real haze, generated by professional haze machines, and O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. To illustrate its usefulness, O-HAZE is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.
引用
收藏
页码:867 / 875
页数:9
相关论文
共 46 条
[1]  
Ancuti Codruta O., 2010, Computer Vision - ACCV 2010. 10th Asian Conference on Computer Vision. Revised Selected Papers, P501, DOI 10.1007/978-3-642-19309-5_39
[2]  
Ancuti C. O., 2010, IEEE ICIP
[3]   Single Image Dehazing by Multi-Scale Fusion [J].
Ancuti, Codruta Orniana ;
Ancuti, Cosmin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (08) :3271-3282
[4]  
Ancuti C, 2016, IEEE IMAGE PROC, P2256, DOI 10.1109/ICIP.2016.7532760
[5]   Effective Contrast-Based Dehazing for Robust Image Matching [J].
Ancuti, Cosmin ;
Ancuti, Codruta O. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (11) :1871-1875
[6]  
[Anonymous], 2007, IEEE COMPUTER VISION
[7]  
[Anonymous], ICISP
[8]  
[Anonymous], 2015, P BRIT MACH VIS C BM
[9]  
[Anonymous], 2002, INT J COMPUTER VISIO
[10]  
[Anonymous], 2004, IEEE C COMP VIS PATT