Single image dehazing via decomposition and enhancement

• Published in: IET image processing Vol. 18; no. 4; pp. 1014 - 1027
• Main Authors: Gu, Bo, Yao, Haohan, Sun, Yanjun, Duan, Zhonghang
• Format: Journal Article
• Language: English
• Published: Wiley 01.03.2024
• Subjects: Bayes methods; image enhancement; image processing; image representation; image restoration; variational techniques
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/ipr2.13003

Hazy images suffer from two problems. The low contrast can be enhanced by estimating a transmission layer, and the colour cast can be restored by estimating an airlight. These two variables, together with the albedo layer, are the constitutive elements of a hazy image. The resulting quality of dehazed images is inextricably linked to the accurate estimation of these components. However, it is ill‐posed to decompose these variables from a single image. As such, this paper presents an innovative algorithm intended to facilitate the optimal decomposition of a hazy image. Using the Markov random field model, an optimal framework is established that allows the simultaneous estimation of the three components across the three‐colour channels. To improve the visual quality, three improvements are proposed in the variational solution for the optimal components. The dehazed result is recomposed from the components with the transmission enhanced to circumvent any potential artefacts or information loss. Extensive experiments on natural images corroborate that the proposed algorithm outperforms state‐of‐the‐art dehazing methods, both qualitatively and quantitatively. The ill‐posed problem of hazy image decomposition is solved through a variational optimisation. The algorithm simultaneously estimates the three physical components of a hazy image in RGB channels. The proposed improvements enhance the quality of conventional image processing methods that are based on variational optimisation.