CGGAN: a context‐guided generative adversarial network for single image dehazing. Issue 15 (18th February 2021)

• Record Type: Journal Article
• Authors: Zhou, Zhaorun; Shi, Zhenghao
• Is Part Of: IET image processing. Volume 14:Issue 15(2020)
• Page Start: 3982
• Page End: 3988
• Publication Date: 2021-02-18
• Subjects: decoding -- feature extraction -- image colour analysis -- image restoration -- image enhancement -- computer vision -- image denoising -- neural nets -- image coding -- image fusion; image haze removal -- context‐guided generative adversarial network -- CGGAN -- single image dehazing -- context‐extraction net -- fusion net -- feature‐extraction net acts -- extracting haze features -- content‐extraction net -- deep features -- generating coarse dehazing image -- final haze‐free image -- multiscale information -- decoding process -- context extraction decoder -- fusion decoder -- extra coarse decoder -- original encoder–decoder -- deep feature information -- different haze scenarios; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.1153
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Image haze removal is highly desired for the application of computer vision. This study proposes a novel context‐guided generative adversarial network (CGGAN) for single image dehazing. Of which, a novel new encoder–decoder is employed as the generator. In addition, it consists of a feature‐extraction net, a context‐extraction net, and a fusion net in sequence. The feature‐extraction net acts as an encoder, and is used for extracting haze features. The content‐extraction net is a multi‐scale parallel pyramid decoder and is used for extracting the deep features of the encoder and generating coarse dehazing image. The fusion net is a decoder and is used for obtaining the final haze‐free image. In order to get better dehazing results, multi‐scale information obtained during the decoding process of the context extraction decoder is used for guiding the fusion decoder. By introducing an extra coarse decoder to the original encoder–decoder, the CGGAN can make better use of the deep feature information extracted by the encoder. To ensure that the proposed CGGAN works effectively for different haze scenarios, different loss functions are employed for the two decoders. Experiments results show the advantage and the effectiveness of the proposed CGGAN, evidential improvements over existing state‐of‐the‐art methods are obtained.