Scholarlink

<p>Single-image dehazing is essential for safety-critical vision systems, yet existing CNN-based methods are often too heavy for edge devices or fail to adapt to spatially varying haze density. This paper introduces HazeWaveNet, a lightweight wavelet-based dehazing network that leverages discrete wavelet transform (DWT) to separate high- and low-frequency components, targeting haze-affected regions while preserving details. A haze-trend guidance mechanism, derived from the dark-channel prior, generates adaptive weight maps that modulate features through factorized convolutions and haze-aware attention modules. Extensive experiments on synthetic and real-world datasets demonstrate that HazeWaveNet achieves competitive performance with significantly lower computational requirements, making it suitable for real-time deployment on resource-constrained platforms.</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

Lightweight single-image dehazing via haze-aware attention and discrete wavelet transform

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月2日

查看全文
  • Yuanyuan Fan,
  • Xifeng Mi

摘要

Single-image dehazing is essential for safety-critical vision systems, yet existing CNN-based methods are often too heavy for edge devices or fail to adapt to spatially varying haze density. This paper introduces HazeWaveNet, a lightweight wavelet-based dehazing network that leverages discrete wavelet transform (DWT) to separate high- and low-frequency components, targeting haze-affected regions while preserving details. A haze-trend guidance mechanism, derived from the dark-channel prior, generates adaptive weight maps that modulate features through factorized convolutions and haze-aware attention modules. Extensive experiments on synthetic and real-world datasets demonstrate that HazeWaveNet achieves competitive performance with significantly lower computational requirements, making it suitable for real-time deployment on resource-constrained platforms.