Haze removal from nighttime images is more difficult compared with daytime image dehazing due to the uneven illumination, low contrast and severe color distortion. In this paper, following approaches based on Dark channel prior, we propose a simple yet effective approach using Retinex theory Taylor series expansion for dehazing, referred as ‘RDT’. Existing methods do not handle shift glow very ...

Image dehazing has always been a challenging topic in image processing. The development of deep learning methods, especially the generative adversarial networks (GAN), provides new way for dehazing. In recent years, many methods based on GAN have applied to However, two problems Firstly, For haze image, not only reduces quality but also blurs details image. network, it is difficult generator re...

Real-world nonhomogeneous haze brings challenges to image restoration. More efforts are needed remove dense and thin simultaneously efficiently. However, most existing dehazing methods do not pay attention the complex distributions of usually suffer from a low runtime speed. To tackle such problems, we present an efficient re-parameterization residual network (RRA-Net), whose design has three k...

Single-image haze removal is a long-standing hurdle for computer vision applications. Several works have been focused on transferring advances from image classification, detection, and segmentation to the niche of dehazing, primarily focusing contrastive learning knowledge distillation. However, these approaches prove computationally expensive, raising concern regarding their applicability on-t...

This paper proposes a novel method for underwater image enhancement algorithm using Principal Component Analysis (PCA) fusion. For fusion process, the dual images are derived using single underwater degraded image. The novelty of this work is the fact that it does not demand any underwater scene parameters beforehand and is independent of prior based information. Secondly, we demonstrated the s...

This paper describes the construction of a layered scene model, based on a single hazy image that has sufficient depth variation. A depth map and radiance image are estimated by standard dehazing methods. The radiance image is then segmented into a small number of clusters, and a corresponding scene plane is estimated for each. This provides the basic structure of a layered scene model, without...