Single Image Haze Removal Based on a Simple Additive Model With Haze Smoothness Prior

Single image haze removal, which is to recover the clear version of a hazy image, is a challenging task in computer vision. In this paper, an additive haze model is proposed to approximate the hazy image formation process. In contrast with the traditional optical model, it regards the haze as an additive layer to a clean image. The model thus avoids estimating the medium transmission rate and the global atmospherical light. In addition, based on a critical observation that haze changes gradually and smoothly across the image, a haze smoothness prior is proposed to constrain this model. This prior assumes that the haze layer is much smoother than the clear image. Benefiting from this prior, we can directly separate the clean image from a single hazy image. Experimental results and comparisons with synthetic images and real-world images demonstrate that the proposed method outperforms state-of-the-art single image haze removal algorithms.

I. Introduction

Images captured outdoors are affected by liquid droplets or small dust particles in the air, collectively known as aerosols. These aerosols absorb the light from the atmosphere and scatter the light reflected from objects in the field of view. These phenomena lead to hazy images, which often suffer from low contrast, faint regions, and color shift. These effects limit the visual quality of images and greatly hinder outdoor computer vision and image processing algorithms. Therefore, research on haze removal is essential.