文献类型：期刊文献

英文题名：Diverse Hazy Image Synthesis via Coloring Network

作者：Zhang, Shengdong[1]; Zhang, Xiaoqin[2]; Wan, Shaohua[3]; Ren, Wenqi[4]; Zhao, Liping[5]; Zhao, Li[2]; Shen, Linlin[6]

机构：[1] Shaoxing University, Shaoxing, Zhejiang, China; [2] College of Computer and Artificial Intelligence, Wenzhou University, Wenzhou, China; [3] Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China; [4] School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China; [5] Department of Computer Science and Engineering, Shaoxing University, Shaoxing, China; [6] College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China

年份：2024

起止页码：1

外文期刊名：IEEE Transactions on Artificial Intelligence

收录：EI(收录号：20241415832269)、Scopus(收录号：2-s2.0-85188941989)

语种：英文

外文关键词：Demulsification - Image processing

外文摘要：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. IEEE