Evaluating Single Image Dehazing Methods Under Realistic Sunlight Haze

TL;DR

This paper introduces Sun-Haze, a benchmark dataset for evaluating single image dehazing methods under realistic sunlight haze, revealing limitations of current techniques in handling non-uniform, colored haze.

Contribution

The paper presents a new dataset and comprehensive evaluation of existing dehazing methods under sunlight haze conditions, highlighting their practical limitations.

Findings

Current methods struggle with non-uniform, colored haze

Sun-Haze dataset reveals gaps in existing dehazing techniques

Evaluation metrics show significant performance degradation

Abstract

Haze can degrade the visibility and the image quality drastically, thus degrading the performance of computer vision tasks such as object detection. Single image dehazing is a challenging and ill-posed problem, despite being widely studied. Most existing methods assume that haze has a uniform/homogeneous distribution and haze can have a single color, i.e. grayish white color similar to smoke, while in reality haze can be distributed non-uniformly with different patterns and colors. In this paper, we focus on haze created by sunlight as it is one of the most prevalent type of haze in the wild. Sunlight can generate non-uniformly distributed haze with drastic density changes due to sun rays and also a spectrum of haze color due to sunlight color changes during the day. This presents a new challenge to image dehazing methods. For these methods to be practical, this problem needs to be addressed. To quantify the challenges and assess the performance of these methods, we present a sunlight haze benchmark dataset, Sun-Haze, containing 107 hazy images with different types of haze created by sunlight having a variety of intensity and color. We evaluate a representative set of state-of-the-art image dehazing methods on this benchmark dataset in terms of standard metrics such as PSNR, SSIM, CIEDE2000, PI and NIQE. This uncovers the limitation of the current methods, and questions their underlying assumptions as well as their practicality.