Joint Transmission Map Estimation and Dehazing Using Deep Networks

Single image haze removal is an extremely challenging problem due to its inherent ill-posed nature. Several prior-based and learning-based methods have been proposed in the literature to solve this problem and they have achieved visually appealing results. However, most of the existing methods assume constant atmospheric light model and tend to follow a two-step procedure involving prior-based methods for estimating transmission map followed by calculation of dehazed image using the closed form solution. In this paper, we relax the constant atmospheric light assumption and propose a novel unified single image dehazing network that jointly estimates the transmission map and performs dehazing. In other words, our new approach provides an end-to-end learning framework, where the inherent transmission map and dehazed result are learned jointly from the loss function. The extensive experiments evaluated on synthetic and real datasets with challenging hazy images demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods.

I. Introduction

Haze is the obscuration of lower atmosphere, typically caused by the presence of suspended particles in the air such as dust, smoke and other dry particulates. The presence of haze usually reduces the visibility range, thus affecting quality of images captured by camera sensors that will be processed by computer vision systems. A sample hazy image is shown on the left side of Figure 1. It can be clearly observed that the existence of haze in an image greatly obscures the background scene. The problem of estimating a clear image from a single hazy input image is commonly referred to as dehazing. Image dehazing has attracted a significant interest in the computer vision and image processing communities in recent years [1]–[16]. Fig. 1.

Sample image dehazing result using the proposed method. Left: Input hazy image. Right: Dehazed result.