Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception
This work addresses the problem of robust perception for autonomous vehicles in low-resource settings, such as Africa's diverse roads, by enabling dataset augmentation without costly data collection, though it is incremental as it builds on existing augmentation techniques.
The paper tackles the scarcity of autonomous vehicle datasets in developing regions, particularly Africa, by developing a procedural augmentation pipeline that simulates refractive distortions and weather-induced artifacts on low-cost dashcam footage, and it provides baseline performance using three image restoration models.
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.