Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Fusion of Heterogeneous Adversarial Networks for Single Image Dehazing

Authors
Park, JaihyunHan, David K.Ko, Hanseok
Issue Date
2020
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Atmospheric modeling; Image color analysis; Training; Scattering; Estimation; Gallium nitride; Generative adversarial networks; Image dehazing; generative adversarial networks; fusion method
Citation
IEEE TRANSACTIONS ON IMAGE PROCESSING, v.29, pp.4721 - 4732
Indexed
SCIE
SCOPUS
Journal Title
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume
29
Start Page
4721
End Page
4732
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/58999
DOI
10.1109/TIP.2020.2975986
ISSN
1057-7149
Abstract
In this paper, we propose a novel image dehazing method. Typical deep learning models for dehazing are trained on paired synthetic indoor dataset. Therefore, these models may be effective for indoor image dehazing but less so for outdoor images. We propose a heterogeneous Generative Adversarial Networks (GAN) based method composed of a cycle-consistent Generative Adversarial Networks (CycleGAN) for producing haze-clear images and a conditional Generative Adversarial Networks (cGAN) for preserving textural details. We introduce a novel loss function in the training of the fused network to minimize GAN generated artifacts, to recover fine details, and to preserve color components. These networks are fused via a convolutional neural network (CNN) to generate dehazed image. Extensive experiments demonstrate that the proposed method significantly outperforms the state-of-the-art methods on both synthetic and real-world hazy images.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Ko, Han seok photo

Ko, Han seok
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE