为非洲低资源驾驶场景生成真实感畸变与天气伪影，助力低成本感知研究。
Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception
- 通过程序化方法模拟低质镜头和空气湍流引起的光学畸变。
- 添加均匀/非均匀雾、镜头眩光等天气伪影，增强数据真实性。
- 开源工具包与数据集，支持非洲地区自动驾驶感知研究。
发展中国家，尤其是非洲多样化的城市、乡村及未铺装道路区域，缺乏自动驾驶车辆数据集，严重制约了低资源环境下感知系统的鲁棒性。本文提出一种程序化增强管道，可对低成本单目行车记录仪视频添加针对非洲复杂驾驶场景的逼真折射畸变与天气伪影。折射模块模拟低质量镜头和空气湍流效应，包括镜头畸变、Perlin噪声、薄板样条（TPS）变形及无散度（不可压缩）形变；天气模块则引入均匀雾、非均匀雾和镜头眩光。为建立基准，我们使用三种图像修复模型提供基线性能。为推动非洲代表性场景下的感知研究，避免高昂的数据采集、标注与仿真成本，我们发布畸变工具包、增强数据集划分及基准结果。
原文摘要 · Abstract (English)
The scarcity of autonomous vehicle datasets from developing regions, particularly across Africa's diverse urban, rural, and unpaved roads, remains a key obstacle to robust perception in low-resource settings. We present a procedural augmentation pipeline that enhances low-cost monocular dashcam footage with realistic refractive distortions and weather-induced artifacts tailored to challenging African driving scenarios. Our refractive module simulates optical effects from low-quality lenses and air turbulence, including lens distortion, Perlin noise, Thin-Plate Spline (TPS), and divergence-free (incompressible) warps. The weather module adds homogeneous fog, heterogeneous fog, and lens flare. To establish a benchmark, we provide baseline performance using three image restoration models. To support perception research in underrepresented African contexts, without costly data collection, labeling, or simulation, we release our distortion toolkit, augmented dataset splits, and benchmark results.
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。