NTIRE 2019 Image Dehazing Challenge Report

This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

1. Introduction

Haze is a common atmospheric phenomenon 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.