计算机与现代化Issue(3)：78-84,7.DOI:10.3969/j.issn.1006-2475.2024.03.013
基于双流Transformer的单幅图像去雾方法
Bi-stream Transformer for Single Image Dehazing
摘要
Abstract
The use of deep learning methods,specifically encoder-decoder networks,has obtained exceptional performance in image dehazing.However,these approaches often solely rely on synthetic datasets for training the models,ignoring prior knowl-edge about hazy images.It presents significant challenges in achieving satisfactory generalization of the trained models,leading to compromised performance on real hazy images.To address this issue and leverage insights from the physical characteristics as-sociated with haze,this paper introduces a novel dual-encoder architecture that incorporates a prior-based encoder into the tradi-tional encoder-decoder framework.By incorporating a feature enhancement module,the representations from the deep layers of the two encoders are effectively fused.Additionally,Transformer blocks are adopted in both the encoder and decoder to address the limitations of commonly used structures in capturing local feature associations.The experimental results show that the pro-posed method not only outperforms state-of-the-art techniques on synthetic data but also exhibits remarkable performance in au-thentic hazy scenarios.关键词
图像去雾/图像恢复/TransformerKey words
image dehazing/image restoration/Transformer分类
信息技术与安全科学引用本文复制引用
李岸然,方阳阳,程慧杰,张申申,阎金强,于腾,杨国为..基于双流Transformer的单幅图像去雾方法[J].计算机与现代化,2024,(3):78-84,7.基金项目
国家自然科学基金面上项目(62172229) （62172229）
