Dehazing is an image enhancing technique that emerged in the recent years. Despite of its importance there is no dataset to quantitatively evaluate such techniques. In this paper we introduce a dataset that contains 1400+ pairs of images with ground truth reference images and hazy images of the same scene. Since due to the variation of illumination conditions recording such images is not feasible, we built a dataset by synthesizing haze in real images of complex scenes. Our dataset, called D-HAZY, is built on the Middelbury [1] and NYU Depth [2] datasets that provide images of various scenes and their corresponding depth maps. Due to the fact that in a hazy medium the scene radiance is attenuated with the distance, based on the depth information and using the physical model of a hazy medium we are able to create a corresponding hazy scene with high fidelity. Finally, using D-HAZY dataset, we perform a comprehensive quantitative evaluation of several state of the art single-image dehazing techniques.

References:

[1] D. Scharstein et al., "High-resolution stereo datasets with subpixel-accurate ground truth.," In GCPR, 2014.

[2] P. Kohli et al, "Indoor segmentation and support inference from rgbd images," in ECCV, 2012.

[3] K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," In IEEE CVPR, 2009.

[4] J.-P. Tarel and N. Hautiere, "Fast visibility restoration from a single color or gray level image," In IEEE ICCV, 2009

[5] C.O. Ancuti and C. Ancuti, "Single image dehazing by multiscale fusion," IEEE Trans. On Image Processing, 2013.

[6] Meng et al., "Efficient image dehazing with boundary constraint and contextual regularization," IEEE ICCV, 2013.

[7] R. Fattal, "Dehazing using color-lines," ACM Trans. On Graph., 2014.

Bibtex

@inproceedings{Ancuti_D-Hazy_ICIP2016,

author = {Cosmin Ancuti, Codruta O. Ancuti, Christophe De Vleeschouwer },

title = {D-HAZY: A DATASET TO EVALUATE QUANTITATIVELY DEHAZING ALGORITHMS},

booktitle = {IEEE International Conference on Image Processing (ICIP) },

series = {ICIP'16},

year = {2016},

location = {Pheonix, USA},

}