This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a reformulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a...

In this letter, we propose a novel and effective haze removal method by using the structure-aware atmospheric veil. More specifically, the initial atmospheric veil is first estimated based on dark channel prior and morphological operator. Furthermore, an energy optimization function considering the structure feature of the input image is constructed to refine the initial atmospheric veil. At la...

Fog and haze can have a dramatic impact on vision systems for land and sea vehicles. The impact of such conditions on infrared images is not as severe as for standard images. By fusing images from two cameras, one ordinary and one near-infrared camera, a complete dehazing system with colour preservation can be achieved. Applying several di erent algorithms to an image set and evaluating the res...

In this study, the requirements for image dehazing methods have been put forward, such as a wider range of scenarios in which can be used, faster processing speeds and higher quality. Recent only unilaterally process daytime or nighttime hazy images. However, we propose an effective single-image technique, dubbed MF Dehazer, order to solve problems associated with dehazing. This technique was d...

We present a method for dehazing images. A dark envelope image is derived with the bilateral minimum filter and a bright envelope is derived with the bilateral maximum filter. The ambient light and transmission of the scene are estimated from these two envelope images. An image without haze is reconstructed from the estimated ambient light and transmission.

Deep learning has made remarkable achievements for single image haze removal. However, existing deep dehazing models only give deterministic results without discussing the uncertainty of them. There exist two types in models: aleatoric that comes from noise inherent observations and epistemic accounts model. In this paper, we propose a novel uncertainty-driven network (UDN) improves by exploiti...

This work addresses the problem of semantic foggy scene understanding (SFSU). Although extensive research has been performed on image dehazing and on semantic scene understanding with weatherclear images, little attention has been paid to SFSU. Due to the difficulty of collecting and annotating foggy images, we choose to generate synthetic fog on real images that depict weather-clear outdoor sc...

The performance of stereo vision tasks degrades when haze exists in the input image pair. Independently applying single dehazing algorithm on left and right images is not optimal. To overcome problem, we propose an effective framework, called SRDNet, for simultaneously images. main idea SRDNet to make full use information from cross views improving performance. It does explicitly employ dispari...

Images obtained under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to overcome t...