Pixel-Wise Wasserstein Autoencoder for Highly Generative Dehazing | IEEE Journals & Magazine | IEEE Xplore

Pixel-Wise Wasserstein Autoencoder for Highly Generative Dehazing


Abstract:

We propose a highly generative dehazing method based on pixel-wise Wasserstein autoencoders. In contrast to existing dehazing methods based on generative adversarial netw...Show More

Abstract:

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.
Published in: IEEE Transactions on Image Processing ( Volume: 30)
Page(s): 5452 - 5462
Date of Publication: 04 June 2021

ISSN Information:

PubMed ID: 34086571

Funding Agency:


References

References is not available for this document.