Abstract
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 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 PSNR and SSIM. Extensive experiments are conducted to show the effectiveness of the proposed model, dataset, and criteria.
Original language | English |
---|---|
Pages (from-to) | 1-10 |
Number of pages | 10 |
Journal | IEEE Transactions on Artificial Intelligence |
DOIs | |
Publication status | Accepted/In press - 2024 |
Externally published | Yes |
Keywords
- Artificial intelligence
- Atmospheric modeling
- Computational modeling
- Diversity
- Evaluation metric
- Hazy image synthesis
- Image color analysis
- Image synthesis
- Real hazy images
- Solid modeling
- Three-dimensional displays
ASJC Scopus subject areas
- Computer Science Applications
- Artificial Intelligence