高级检索
    张琪东, 迟静, 陈玉妍, 张彩明. 基于雾浓度分类与暗-亮通道先验的多分支去雾网络[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202220812
    引用本文: 张琪东, 迟静, 陈玉妍, 张彩明. 基于雾浓度分类与暗-亮通道先验的多分支去雾网络[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202220812
    Zhang Qidong, Chi Jing, Chen Yuyan, Zhang Caiming. A Multi-Branch Defogging Network Based on Fog Concentration Classification and Dark and Bright Channel Priors[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202220812
    Citation: Zhang Qidong, Chi Jing, Chen Yuyan, Zhang Caiming. A Multi-Branch Defogging Network Based on Fog Concentration Classification and Dark and Bright Channel Priors[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202220812

    基于雾浓度分类与暗-亮通道先验的多分支去雾网络

    A Multi-Branch Defogging Network Based on Fog Concentration Classification and Dark and Bright Channel Priors

    • 摘要: 在图像去雾领域中,目前多数去雾模型难以维持精度与效率的平衡,高精度的模型往往伴随着复杂的网络结构,而简单的网络结构又往往会导致低质量的结果. 针对该问题提出1个基于雾浓度分类与暗-亮通道先验的多分支去雾模型,通过对带雾图像分类,使用复杂度不同的网络来处理不同雾浓度的图像,可在保证精度的同时提高计算效率. 模型由轻量级雾图像分类器和基于暗-亮通道先验的多分支去雾网络2部分构成:前者将带雾图像分为轻雾、中雾、浓雾3类,输出雾浓度标签;后者包含3个结构相同、宽度不同的分支网络,根据雾浓度标签选择不同的分支网络处理不同雾浓度图像,恢复至无雾图像. 提出1个新的雾浓度分类方法以及基于该方法的雾浓度分类损失函数,可根据带雾图像的暗通道特征和恢复难度,结合生成图像质量和模型计算效率,得到对带雾图像合理准确的分类结果,达到去雾效果和算力需求的良好平衡. 提出新的暗通道与亮通道先验损失函数,用于约束分支去雾网络,可有效提高去雾精度. 实验结果表明,模型能够以更低的网络参数量和复杂度得到更优的去雾结果.

       

      Abstract: In the field of image defogging, it is difficult for most defogging models to maintain a balance between accuracy and efficiency. Specifically, high-precision models are often accompanied by complex network structures, and simple network structures often lead to low-quality results. To address the problem, we propose a multi-branch defogging network based on fog concentration classification and dark and bright channel priors. The model uses the defogging networks with different complexity to handle the images with different fog concentrations, which significantly raises the computational efficiency under ensuring the defogging precision. The model is composed of a lightweight foggy image classifier and a multi-branch defogging network. The classifier divides the foggy images into light, medium and dense foggy images and outputs the fog concentration labels. The multi-branch network contains three branches with the same structure but different widths that process three types of fog images separately. We propose a new fog concentration classification method and a new fog concentration classification loss function. The function combines the dark channel characteristics and defogging difficulty of the foggy image with the defogging precision and computational efficiency of the model, so as to obtain a reasonable fog concentration classification, and consequently achieve a good balance of defogging quality and computing power requirements. We propose a new dark channel prior loss function and a new bright channel prior loss function to constrain the multi-branch defogging network, which effectively enhance the defogging precision. Extensive experiments show that the model is beneficial to get better defogging effect with lower network parameters and complexity.

       

    /

    返回文章
    返回