通过交互引导提升去雾效果，让卷积和Transformer各取所长。
Interaction-Guided Two-Branch Image Dehazing Network
- 双分支结构让CNN与Transformer相互引导，利用全局注意力定位局部特征。
- 在合成与真实数据集上均达到领先水平，尤其在复杂雾霾场景表现优异。
- 适合需要高细节还原的图像恢复任务，如自动驾驶与遥感成像。
图像去雾旨在从有雾图像中恢复清晰图像。卷积神经网络（CNN）和Transformer分别在局部与全局特征提取上表现出色，目前已成为图像去雾的两大主流框架。本文提出一种新型双分支去雾框架，实现CNN与Transformer组件间的交互引导。通过分析全局与局部特征之间的差异关系，重新利用其互补特性，使全局注意力图能够指导CNN聚焦于有效特征位置，从而提升局部特征捕捉精度。单分支设计的Transformer则保障了网络对全局信息的恢复能力。大量实验表明，该方法在合成与真实公开数据集上均取得具有竞争力的定性和定量性能。代码已开源：https://github.com/Feecuin/Two-Branch-Dehazing。
原文摘要 · Abstract (English)
Image dehazing aims to restore clean images from hazy ones. Convolutional Neural Networks (CNNs) and Transformers have demonstrated exceptional performance in local and global feature extraction, respectively, and currently represent the two mainstream frameworks in image dehazing. In this paper, we propose a novel dual-branch image dehazing framework that guides CNN and Transformer components interactively. We reconsider the complementary characteristics of CNNs and Transformers by leveraging the differential relationships between global and local features for interactive guidance. This approach enables the capture of local feature positions through global attention maps, allowing the CNN to focus solely on feature information at effective positions. The single-branch Transformer design ensures the network's global information recovery capability. Extensive experiments demonstrate that our proposed method yields competitive qualitative and quantitative evaluation performance on both synthetic and real public datasets. Codes are available at https://github.com/Feecuin/Two-Branch-Dehazing
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。