用光照先验指导网络，高效恢复雾霾图像细节。
Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing
- 融合亮/暗通道与直方图均衡先验，引导特征学习
- 双模块设计：先验聚合+特征均衡，提升去雾质量
- 结构轻量，适合实时去雾应用，尤其适合移动端
图像去雾是恢复退化图像清晰度与纹理的关键任务。尽管视觉变换器在多种去雾任务中表现优异，但其二次复杂度及缺乏去雾先验限制了其实用性。本文基于亮通道先验（BCP）、暗通道先验（DCP）和直方图均衡（HE）三重先验，提出一种优先引导的分层调和网络（PGH²Net）。该网络采用类UNet结构，包含高效编码器与解码器，由两种模块构成：(1) 先验聚合模块，注入BCP/DCP信息并利用门控注意力选择多样上下文；(2) 特征调和模块，从空间与通道维度减去低频成分，学习更丰富的特征分布以均衡特征图。
原文摘要 · Abstract (English)
Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a \textit{P}rior-\textit{g}uided Hierarchical \textit{H}armonization Network (PGH$^2$Net) for image dehazing. PGH$^2$Net is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects B/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。