This paper proposes a Dynamic Multi-Attention Dehazing Network (DMADN) for single image dehazing. The proposed network consists of two key components, the Feature Attention (DFA) module, and Adaptive Fusion (AFF) module. DFA module provides pixel-wise weights channel-wise input features, considering that haze distribution is always uneven in degenerated value each channel different. We propose ...

The reliable method for dehazing in video was proposed by using haze removal algorithm. The simple but effective prior is change of detail prior (CoD) algorithm to remove haze from video. By using Change of detail prior algorithm we can estimate the thickness of Haze from every frame and also effectively recover a high quality video. In this approach first extract the background image by using ...

This study proposes a hybrid of a recurrent fuzzy cerebellar model articulation controller (RFCMAC) and a weighted strategy for solving single-image visibility in a degraded image. The proposed RFCMACmodel is used to estimate the transmission map. The average value of the brightest 1% in a hazy image is calculated for atmospheric light estimation. A new adaptive weighted estimation is then used...

-Because of the strong and successfulness, tampering of digital images depends upon the flexible architecture for a derivative estimation has become an important method to a spectacle for a large number of approaches. Regulated on an inherent range, the tampering of digital image procedure is varied and carried out. The beginning of a bridging origination which dilutes into a simple procedure. ...

This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes. The survey begins with discussing the optical models of atmospheric scattering media and image formation. This is followed by a survey of existing methods, which are grouped to multiple image methods, polarizing filters based methods, methods with known depth, and s...

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve dehazing without training on the ground-truth clean (unsupervised) an collection (untrained). An unsupervised model will avoid intensive labor of collecting hazy-clean pairs, untrained is a “real” approach which could remove haze based observed hazy only no extra...

In this paper, we present a powerful underwater image dehazing technique that exploits two characteristics—RGB color channels and features. using RGB channels, each channel is decomposed into units based on the similarities via k-mean. This markedly improves adaptability identification of similar pixels, thus reduces pixels with weak correlation, leaving only higher correlation. We use an infin...

Single image dehazing is a challenging ill-posed problem that has drawn significant attention in the last few years. Recently, convolutional neural networks have achieved great success dehazing. However, it still difficult for these increasingly complex models to recover accurate details from hazy image. In this paper, we pay feature extraction and utilization of input itself. To achieve this, ...