The sky regions of foggy image processed by all the existing conventional dehazing methods are degraded by color distortion and severe noise. This paper proposes an improved algorithm which combines dark channel prior and inverse image. We first invert the foggy image, and then estimate the transmission of the inverse image. At last, compared with the non-inversed transmission, the larger value...

Research on image dehazing has made the need for a suitable dehazed quality assessment (DIQA) method even more urgent. The performance of existing DIQA methods heavily relies handcrafted haze-related features. Since hazy images with uneven haze density distributions will result in after dehazing, manually extracted feature expression is neither accurate nor robust. In this paper, we design deep...

Haze reduces the contrast of an image and causes loss in colors, which has a negative effect on subsequent object detection; therefore, single dehazing is challenging visual task. In addition, defects exist previous existing approaches: Pixel-based approaches are likely to result insufficient information estimate transmission, whereas patch-based ones prone generate shadows. They both also tend...

In this paper, we propose an efficient algorithm to directly restore a clear image from hazy input, which can be adapted for nighttime dehazing. The proposed hinges on trainable neural network realized in encoder–decoder architecture. encoder is exploited capture the context of derived input images, while decoder employed estimate contribution each final dehazed result using learned representat...

Single image dehazing is a prerequisite that affects the performance of many visually related tasks and has attracted increasing attention in recent years. However, most existing methods place more emphasis on haze removal but less detail recovery dehazed images. In this paper, we propose single method with an independent Detail Recovery Network (DRN), which considers capturing details from inp...

Underwater image enhancement and turbidity removal (dehazing) is a very challenging problem, not only due to the sheer variety of environments where it applicable, but also lack high-resolution, labelled data. In this paper, we present novel, two-step deep learning approach for underwater dehazing colour correction. iDehaze, leverage computer graphics physically model light propagation in condi...

Despite the great progress that has been made in task of single image dehazing, results existing models restoring edge and texture information are still challenging. Besides, most dehazing trained on synthetic data, resulting poor generalization ability to real-world images. To address aforementioned problems, a semi-supervised learning method based decomposition model Osher, Solé, Vese(The OSV...

Intra-domain and inter-domain gaps are widely presented in image processing tasks due to data distribution differences. In the field of dehazing, particular previous works have paid attention gap between synthetic domain real domain. However, those methods only establish connection from without considering significant shift within (intra-domain gap). this work, we propose a Two-Step Dehazing Ne...