Scholarlink

<p>To solve the problem that existing dehazing algorithms have difficulty in capturing paired hazy and clear images in the real world, while unpaired real-world hazy and clear images are readily obtained. In this study, unpaired real-world hazy and clear images are used to realize unsupervised dehazing. Inspired by the Generative Adversarial Network framework, the generator network combines multi-scale dense blocks and attention mechanism and uses adaptive blending operation to speed up network training while ensuring effective delivery of image details. By incorporating contrastive learning, a weighted contrastive loss function is introduced, which encourages the recovered image to be close to positive samples and away from negative samples in the embedding space. Meanwhile, multiple loss functions are combined to enhance the generalization ability of the generative adversarial network in order to train the network more effectively. The proposed algorithm is tested on an outdoor public dataset, and the experimental results show that the algorithm has better performance than existing unsupervised dehazing algorithms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Unsupervised dehazing of multi-scale residuals based on weighted contrastive learning

  • 期刊论文

  • 发表日期：

    2025年4月5日

查看全文
  • Jianing Wang,
  • Yongsheng zhang,
  • Zuoyang Liu

摘要

To solve the problem that existing dehazing algorithms have difficulty in capturing paired hazy and clear images in the real world, while unpaired real-world hazy and clear images are readily obtained. In this study, unpaired real-world hazy and clear images are used to realize unsupervised dehazing. Inspired by the Generative Adversarial Network framework, the generator network combines multi-scale dense blocks and attention mechanism and uses adaptive blending operation to speed up network training while ensuring effective delivery of image details. By incorporating contrastive learning, a weighted contrastive loss function is introduced, which encourages the recovered image to be close to positive samples and away from negative samples in the embedding space. Meanwhile, multiple loss functions are combined to enhance the generalization ability of the generative adversarial network in order to train the network more effectively. The proposed algorithm is tested on an outdoor public dataset, and the experimental results show that the algorithm has better performance than existing unsupervised dehazing algorithms.