Deep multi-scale network for single image dehazing with self-guided maps

Liu, Jianlei; Yu, Hao; Zhang, Zhongzheng; Chen, Chen; Hou, Qianwen

doi:10.1007/s11760-023-02505-2

Cited by 3 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first is to explore more general image restoration methods, which is not only suitable for image haze removal, but also suitable for image rain removal [29][30][31], image noise removal [32][33][34], etc. The second one is to explore the removal of haze in more complex scenes, such as dense haze scenes [35][36][37] and nightlight haze scenes [38][39][40].…”

Section: Discussionmentioning

confidence: 99%

Black-box Dehazing Network via Joint Loss Function

Zhang,

Zhao,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

Single image dehazing is a notoriously challenging task in image processing due to the numerous unknown factors involved. Most existing dehazing methods are based on physical models of the haze formation process. However, real-world haze scenes cannot be accurately mathematically modeled due to the existence of various unquantifiable factors in the scene. Therefore, the dehazing methods based on physical models often perform poorly in complex haze scenes. In this paper, we propose a novel black-box dehazing equation. In this equation, the haze is modelled as an additional image interference layer, without explicitly reasoning about the physical model of haze formation. The dehazing process is modelled as removing this image interference layer. Based on this equation, we propose a novel network architecture called the Black-box Dehazing Network (BDN). Moreover, we propose a joint loss function for training this network. The joint loss function not only evaluates pixel-level differences between the dehazed image and the haze-free image, but also measures differences in texture, color, and structure between the hazy image and its corresponding dehazed version as well as those between the hazy image and its haze-free version. In training, BDNet is only fed pairs of haze-free images and their corresponding hazy images. The corresponding hazy patches are generated on-the-fly during network training. Experimental results demonstrate that the proposed method has the advantage of universality and outperforms existing state-of-the-art dehazing methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Black-box Dehazing Network via Joint Loss Function

Zhang,

Zhao,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Single image dehazing method based on knowledge transfer and multi-branch data augmentation correction

Cao

2024

SIViP

View full text Add to dashboard Cite

Single image dehazing method based on knowledge transfer and multi-branch data augmentation correction

Cao

2024

Preprint

View full text Add to dashboard Cite

Dehazing can improve the clarity of images and provide more reliable inputs for image analysis tasks, thereby enhancing their performance. Therefore, we propose a dehazing network based on knowledge transfer and multi-data enhancement correction. First, we propose a multi-data enhancement correction method that combines different image enhancement techniques to improve the quality of the input images. Second, by leveraging a pre-trained teacher network to acquire prior knowledge from clear data, guiding the dehazing process of the student network through knowledge transfer. We introduce a deep multi-scale refinement network composed of a dense feature enhancement module and enhanced residual dense blocks, enabling the dehazing model to learn the local structure and feature representation of the data more accurately. Experimental results on multiple benchmark datasets demonstrate that the proposed dehazing method outperforms state-of-the-art dehazing methods. Code are available at: https://github.com/JNcmm/KTMDA-DehazeNet.

show abstract

Deep multi-scale network for single image dehazing with self-guided maps

Cited by 3 publications

References 33 publications

Black-box Dehazing Network via Joint Loss Function

Black-box Dehazing Network via Joint Loss Function

Single image dehazing method based on knowledge transfer and multi-branch data augmentation correction

Single image dehazing method based on knowledge transfer and multi-branch data augmentation correction

Contact Info

Product

Resources

About