用预训练深度特征提升图像去雾效果，适配多种模型架构。
Can Large Pretrained Depth Estimation Models Help With Image Dehazing?
- 利用海量图像预训练的深度特征，跨场景保持一致性。
- 提出即插即用的RGB-D融合模块，兼容多种去雾网络。
- 在多个数据集上验证有效，适合需要高效部署的场景。
图像去雾因真实场景中雾霾的空间变化性而极具挑战。尽管现有方法展示了大规模预训练模型在去雾中的潜力，但其特定架构设计限制了在不同精度与效率需求场景下的适应性。本文系统研究了从数百万张多样化图像中学习到的预训练深度表征在去雾任务中的泛化能力。实证分析表明，所学深度特征在不同雾霾程度下仍保持显著一致性。基于此，我们提出一种即插即用的RGB-D融合模块，可无缝集成于多种去雾架构中。在多个基准上的大量实验验证了该方法的有效性与广泛适用性。
原文摘要 · Abstract (English)
Image dehazing remains a challenging problem due to the spatially varying nature of haze in real-world scenes. While existing methods have demonstrated the promise of large-scale pretrained models for image dehazing, their architecture-specific designs hinder adaptability across diverse scenarios with different accuracy and efficiency requirements. In this work, we systematically investigate the generalization capability of pretrained depth representations-learned from millions of diverse images-for image dehazing. Our empirical analysis reveals that the learned deep depth features maintain remarkable consistency across varying haze levels. Building on this insight, we propose a plug-and-play RGB-D fusion module that seamlessly integrates with diverse dehazing architectures. Extensive experiments across multiple benchmarks validate both the effectiveness and broad applicability of our approach.
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。