Single Image Dehazing via Model-Based Deep-Learning

Single Image Dehazing via Model-Based Deep-Learning

2022 IEEE International Conference on Image Processing (ICIP)

10.1109/ICIP46576.2022.9897479

https://ieeexplore.ieee.org/document/9897479

Zhengguo Li, Chaobing Zheng, Haiyan Shu, Shiqian Wu

Electrical and Electronic Engineering, image processing

18 October 2022

Z. Li, C. Zheng, H. Shu and S. Wu, & Single Image Dehazing via Model-Based Deep-Learning, 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 141-145, doi: 10.1109/ICIP46576.2022.9897479.

Model-based single image dehazing algorithms restore images with sharp edges and rich details at the expense of low PSNR values. Data-driven ones restore images with high PSNR values but with low contrast, and even some remaining haze. In this paper, a novel single image dehazing algorithm is introduced by integrating model-based and data-driven approaches. Both transmission map and atmospheric light are initialized by the model-based methods, and refined by deep learning based approaches which form a neural augmentation. Haze-free images are restored by using the transmission map and atmospheric light. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.

Publisher Copyright

There was no specific funding for the research done

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18728

978-1-6654-9620-9

Institute for Infocomm Research