NTIRE 2018 Challenge on Image Dehazing: Methods and Results

This paper reviews the first challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The challenge had 2 tracks. Track 1 employed the indoor images (using I-HAZE dataset), while Track 2 outdoor images (using O-HAZE dataset). The hazy images have been captured in presence of real haze, generated by professional haze machines. I-HAZE dataset contains 35 scenes that correspond to indoor domestic environments, with objects with different colors and specularities. O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. The dehazing process was learnable through provided pairs of haze-free and hazy train images. Each track had ~ 120 registered participants and 21 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

1. Introduction

Haze is a common atmospheric phenomena produced by small floating particles that reduce the visibility of distant objects due to light scattering and attenuation. This results in a loss of local contrast for distant objects, in the addition of noise to the image, and in a selective attenuation of the light spectrum. Image dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years.