Fusion of Heterogeneous Adversarial Networks for Single Image Dehazing

Jaihyun Park, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

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.

Original languageEnglish
Article number9018375
Pages (from-to)4721-4732
Number of pages12
JournalIEEE Transactions on Image Processing
Volume29
DOIs
Publication statusPublished - 2020 Jan 1

Keywords

  • fusion method
  • generative adversarial networks
  • Image dehazing

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Fusion of Heterogeneous Adversarial Networks for Single Image Dehazing'. Together they form a unique fingerprint.

  • Cite this