Diverse Hazy Image Synthesis via Coloring Network

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

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.
BibTeX
@article{zhang2024diverse,
  author = {Shengdong Zhang and Xiaoqin Zhang and Shaohua Wan and Wenqi Ren and Liping Zhao and Li Zhao and Linlin Shen},
  title = {{Diverse Hazy Image Synthesis via Coloring Network}},
  journal = {IEEE Trans. Artif. Intell.},
  year = {2024},
  url = {https://openreview.net/forum?id=plHEH8UErg},
}

Loading related content...

Figure