针对不同浓雾程度动态优化去雾与目标检测，提升雾霾环境视觉准确性。
ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
- 按雾密度分级路由图像，分三阶段自适应处理
- 在真实数据集上检测精度提升13点，去雾质量提高2.1 dB
- 兼顾速度与效果，适合自动驾驶等实时系统
恶劣天气（尤其是雾）严重损害视觉信息，对自动驾驶、监控等安全关键应用构成挑战。本文提出ADAM-Dehaze，一种自适应密度感知的多阶段去雾框架，联合优化不同雾浓度下的图像恢复与目标检测。轻量级霾密度估计网络（HDEN）将输入分类为轻度、中度或重度雾，系统据此动态选择对应轻、中、复杂三个CORUN分支进行处理。引入新型自适应损失函数，平衡物理模型一致性与感知保真度，确保去雾准确并保留细节。在Cityscapes和真实世界RTTS基准上，ADAM-Dehaze使PSNR最高提升2.1 dB，FADE降低30%，目标检测mAP最高提升13点，同时推理时间减少20%。结果表明，按强度区分处理与下游任务无缝集成的重要性。代码已公开：https://github.com/talha-alam/ADAM-Dehaze。
原文摘要 · Abstract (English)
Adverse weather conditions, particularly fog, pose a significant challenge to autonomous vehicles, surveillance systems, and other safety-critical applications by severely degrading visual information. We introduce ADAM-Dehaze, an adaptive, density-aware dehazing framework that jointly optimizes image restoration and object detection under varying fog intensities. A lightweight Haze Density Estimation Network (HDEN) classifies each input as light, medium, or heavy fog. Based on this score, the system dynamically routes the image through one of three CORUN branches: Light, Medium, or Complex, each tailored to its haze regime. A novel adaptive loss balances physical-model coherence and perceptual fidelity, ensuring both accurate defogging and preservation of fine details. On Cityscapes and the real-world RTTS benchmark, ADAM-Dehaze improves PSNR by up to 2.1 dB, reduces FADE by 30 percent, and increases object detection mAP by up to 13 points, while cutting inference time by 20 percent. These results highlight the importance of intensity-specific processing and seamless integration with downstream vision tasks. Code available at: https://github.com/talha-alam/ADAM-Dehaze.
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。