DD-CycleGAN: Unpaired image dehazing via Double-Discriminator Cycle-Consistent Generative Adversarial Network. (June 2019)

• Record Type: Journal Article
• Authors: Zhao, Jingming; Zhang, Juan; Li, Zhi; Hwang, Jenq-Neng; Gao, Yongbin; Fang, Zhijun; Jiang, Xiaoyan; Huang, Bo
• Is Part Of: Engineering applications of artificial intelligence. Volume 82(2019)
• Page Start: 263
• Page End: 271
• Publication Date: 2019-06
• Subjects: Haze removal -- Generative adversarial network; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2019.04.003
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Despite the recent progress in image dehazing, the task remains tremendous challenging. To improve the performance of haze removal, we propose a scheme for haze removal based on Double-Discriminator Cycle-Consistent Generative Adversarial Network (DD-CycleGAN), which leverages CycleGAN to translate a hazy image to the corresponding haze-free image. Unlike other methods, it does not need pairs of haze and their corresponding haze-free images for training. Extensive experiments demonstrate that the proposed method achieves significant improvements over the existing methods, both quantitatively as well as qualitatively. And our method can also achieve good effects qualitatively when applied to the real scenes too.