Pixel-wise Wasserstein Autoencoder for Highly Generative Dehazing

• Published in: IEEE transactions on image processing Vol. 30; p. 1
• Main Authors: Kim, Guisik, Park, Sung Woo, Kwon, Junseok
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Channel estimation; Dehazing; Estimation; Generative adversarial networks; Haze; Image enhancement; Lighting; Network architecture; Pixels; Tensors; Transforms; Wasserstein autoencoder
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2021.3084743

We propose a highly generative dehazing method based on pixel-wise Wasserstein autoencoders. In contrast to existing dehazing methods based on generative adversarial networks, our method can produce a variety of dehazed images with different styles. It significantly improves the dehazing accuracy via pixel-wise matching from hazy to dehazed images through 2-dimensional latent tensors of the Wasserstein autoencoder. In addition, we present an advanced feature fusion technique to deliver rich information to the latent space. For style transfer, we introduce a mapping function that transforms existing latent spaces to new ones. Thus, our method can produce highly generative haze-free images with various tones, illuminations, and moods, which induces several interesting applications, including low-light enhancement, daytime dehazing, nighttime dehazing, and underwater image enhancement. Experimental results demonstrate that our method quantitatively outperforms existing state-of-the-art methods for synthetic and real-world datasets, and simultaneously generates highly generative haze-free images, which are qualitatively diverse.