计算机科学与探索2025，Vol.19Issue(10)：2722-2738,17.DOI:10.3778/j.issn.1673-9418.2503070
结合多尺度处理和轻量级网络的单幅图像去雾算法
Single Image Dehazing Algorithm Integrating Multi-scale Processing with Light-weight Network
摘要
Abstract
To address the issues of halo artifacts,edge blurring,color distortion,and contrast imbalance commonly en-countered in traditional physical model-based dehazing algorithms,this paper proposes a single-image dehazing algorithm integrating multi-scale processing and lightweight networks.Initially,this paper generates images with varying exposure levels to capture texture features across different illumination regions,enabling comprehensive scene characterization through fusion of dark channel information under multi-exposure conditions.Subsequently,wavelet transform is em-ployed to integrate multi-scale dark channel prior transmission estimates with multi-scale gamma-corrected image trans-mission estimates,which are further optimized using unsharp mask-guided filtering to enhance edge preservation capabili-ties.An adaptive regularization constraint mechanism is introduced to dynamically adjust smoothing intensity,effectively balancing detail retention and noise suppression.Finally,multi-scale luminance guidance combined with a lightweight net-work is adopted for atmospheric light estimation,enabling haze-free image reconstruction through inverse atmospheric scattering model computation.Extensive quantitative and qualitative experiments conducted on SOTS,RTTS,and HSTS datasets demonstrate that compared with conventional dehazing algorithms,the proposed method exhibits superior perfor-mance in both objective metrics and subjective visual quality,particularly showing enhanced restoration effectiveness in regions with abrupt depth variations.关键词
图像去雾/图像融合/伽玛校正/非锐化掩膜/暗通道先验Key words
image dehazing/image fusion/gamma correction/unsharp mask/dark channel prior分类
信息技术与安全科学引用本文复制引用
谭永前,曾凡菊..结合多尺度处理和轻量级网络的单幅图像去雾算法[J].计算机科学与探索,2025,19(10):2722-2738,17.基金项目
贵州省2022年度基础研究计划(自然科学)(黔科合基础-ZK[2022]一般526) （自然科学）
贵州省高层次创新型人才培养"千层次"项目(黔千层人才[2025]202308) （黔千层人才[2025]202308）
凯里学院"十四五"学科专业平台团队一体化建设规划项目(YTH-TD2024001).This work was supported by the Guizhou Provincial Basic Research Program(Natural Science)(QKH Foundation-ZK[2022]General 526),the High-Level Innovative Talents Cultivation"Qianceng Program"of Guizhou Province([2025]Qian Talents 202308),and the Kaili University"14th Five-Year Plan"Integrated Construction Project for Discipline Specialties,Platforms,and Team Development(YTH-TD2024001). （YTH-TD2024001）
