融合注意力机制与循环对抗网络，实现无配对图像去雾、去雪、去雨。
Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
- 用特征融合注意力网络捕捉细节，结合CycleGAN处理无配对数据
- 在RESIDE和DenseHaze数据集上提升PSNR和SSIM，优于传统方法
- 适合图像增强、自动驾驶等需清晰视觉的场景
本文提出一种结合特征融合注意力（FFA）网络与CycleGAN架构的新方法，用于图像去雾。该方法融合有监督与无监督学习，有效去除雾霾并保留关键图像细节。在RESIDE和DenseHaze CVPR 2019数据集上的大量实验表明，该方法能同时处理合成与真实世界雾霾图像，性能显著优于传统去雾方法，在图像质量指标上实现更高PSNR和SSIM。CycleGAN有效应对雾霾图与清晰图无配对的问题，使模型可在无需成对数据的情况下学习映射关系。
原文摘要 · Abstract (English)
This paper presents a novel approach to image dehazing by combining Feature Fusion Attention (FFA) networks with CycleGAN architecture. Our method leverages both supervised and unsupervised learning techniques to effectively remove haze from images while preserving crucial image details. The proposed hybrid architecture demonstrates significant improvements in image quality metrics, achieving superior PSNR and SSIM scores compared to traditional dehazing methods. Through extensive experimentation on the RESIDE and DenseHaze CVPR 2019 dataset, we show that our approach effectively handles both synthetic and real-world hazy images. CycleGAN handles the unpaired nature of hazy and clean images effectively, enabling the model to learn mappings even without paired data.
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。