Diverse Hazy Image Synthesis via Coloring Network

Shengdong Zhang, Xiaoqin Zhang, Shaohua Wan, Wenqi Ren, Liping Zhao, Li Zhao, Linlin Shen

Research output: Journal PublicationArticlepeer-review

1 Citation (Scopus)

Abstract

Convolutional neural network (CNN)-based dehazing methods have achieved great success in single image dehazing. However, the absence of real-world haze image datasets hinders the deep development of single image dehazing. To address this issue, we propose a diverse hazy image synthesis method based on generative adversarial network (GAN) and matting. Specially, we train a GAN-based model that can transform a gray image into a hazy image. To boost the diversity of hazy images, we propose to simulate hazy images via image matting, which can fuse a real haze image with another image containing diverse objects. To evaluate the performance of dehazing methods, we propose two novel metrics: part-based peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM). Extensive experiments are conducted to show the effectiveness of the proposed model, dataset, and criteria.

Original languageEnglish
Pages (from-to)3703-3713
Number of pages11
JournalIEEE Transactions on Artificial Intelligence
Volume5
Issue number7
DOIs
Publication statusPublished - 2024
Externally publishedYes

Keywords

  • Diversity
  • evaluation metric
  • hazy image synthesis
  • real hazy images

ASJC Scopus subject areas

  • Computer Science Applications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Diverse Hazy Image Synthesis via Coloring Network'. Together they form a unique fingerprint.

Cite this