Journal article
Fusion of Heterogeneous Adversarial Networks for Single Image Dehazing
IEEE transactions on image processing, v 29, pp 4721-4732
01 Jan 2020
PMID: 32142439
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.
Metrics
Details
- Title
- Fusion of Heterogeneous Adversarial Networks for Single Image Dehazing
- Creators
- Jaihyun Park - Korea UniversityDavid K. Han - DEVCOM Army Research LaboratoryHanseok Ko - Korea University
- Publication Details
- IEEE transactions on image processing, v 29, pp 4721-4732
- Publisher
- IEEE
- Number of pages
- 12
- Grant note
- Brain Korea 21 Plus Project in 2019
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000526697100005
- Scopus ID
- 2-s2.0-85081957368
- Other Identifier
- 991021931088904721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Engineering, Electrical & Electronic