用小波变换和对比学习提升真实场景去雾效果
WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning
- 结合小波变换与对比学习，增强特征表达能力
- 在真实图像上优于现有方法，鲁棒性更强
- 适合自动驾驶、监控等真实场景应用
户外雾霾环境下拍摄的图像常出现色彩失真、对比度低、细节丢失等问题，影响高层视觉任务。单图像去雾对自动驾驶、监视等应用至关重要，旨在恢复图像清晰度。本文提出WTCL-Dehaze，一种融合对比损失与离散小波变换（DWT）的半监督去雾网络。通过对比模糊与清晰图像对来增强特征表示，并利用DWT进行多尺度特征提取，有效捕捉高频细节与全局结构。模型结合标注与未标注数据，缓解域差距，提升泛化能力。在合成与真实世界数据集联合训练下，实验表明该方法在基准数据集及真实图像上均显著优于当前最优单图像去雾算法。
原文摘要 · Abstract (English)
Images captured in hazy outdoor conditions often suffer from colour distortion, low contrast, and loss of detail, which impair high-level vision tasks. Single image dehazing is essential for applications such as autonomous driving and surveillance, with the aim of restoring image clarity. In this work, we propose WTCL-Dehaze an enhanced semi-supervised dehazing network that integrates Contrastive Loss and Discrete Wavelet Transform (DWT). We incorporate contrastive regularization to enhance feature representation by contrasting hazy and clear image pairs. Additionally, we utilize DWT for multi-scale feature extraction, effectively capturing high-frequency details and global structures. Our approach leverages both labelled and unlabelled data to mitigate the domain gap and improve generalization. The model is trained on a combination of synthetic and real-world datasets, ensuring robust performance across different scenarios. Extensive experiments demonstrate that our proposed algorithm achieves superior performance and improved robustness compared to state-of-the-art single image dehazing methods on both benchmark datasets and real-world images.
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。