Pixel-Wise Wasserstein Autoencoder for Highly Generative Dehazing
- Authors
- Kim, Guisik; Park, Sung Woo; Kwon, Junseok
- Issue Date
- Jun-2021
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Tensors; Image enhancement; Lighting; Network architecture; Estimation; Channel estimation; Transforms; Dehazing; wasserstein autoencoder; image enhancement
- Citation
- IEEE TRANSACTIONS ON IMAGE PROCESSING, v.30, pp 5452 - 5462
- Pages
- 11
- Journal Title
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- Volume
- 30
- Start Page
- 5452
- End Page
- 5462
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/47752
- DOI
- 10.1109/TIP.2021.3084743
- ISSN
- 1057-7149
1941-0042
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.