O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images
(2018) New Trends in Image Restoration and Enhancement workshop, in IEEE Computer Vision and Pattern Recognition (17.June.2018)
Files
Ancuti_O-HAZE_A_Dehazing_CVPR_2018_paper.pdf
Open Access - Adobe PDF
- 3.25 MB
Details
- Authors
- Abstract
- 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 realhaze, generated by professional haze machines, and O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy set of state-of-the-art dehazing techniques, usingtraditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.
- Affiliations
Citations
Codruta Ancuti, Cosmin Ancuti, Radu Timofte, & De Vleeschouwer, C. (2018). O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. Proceedings of the New Trends in Image Restoration and Enhancement workshop, in conjunction with CVPR. Published. New Trends in Image Restoration and Enhancement workshop, in IEEE Computer Vision and Pattern Recognition. https://hdl.handle.net/2078.5/221524