Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception

2025/07/07 by Moseli Mots'oehli, Mots'oehli, Moseli, Hok Wai Chan +10 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Enhancement Techniques #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2507.05536

openalex publication_date 2025/07/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Diffusion Restoration Adapter for Real-World Image Restoration
• SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
• Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond
• Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation
• Scalable Diffusion Models with Transformers
• Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather
• Public Parking Spot Detection And Geo-localization Using Transfer Learning
• Palette: Image-to-Image Diffusion Models
• LoRA: Low-Rank Adaptation of Large Language Models
• SegFormer: Simple and Efficient Design for Semantic Segmentation with\n Transformers
• Denoising Diffusion Probabilistic Models
• UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
• Divergence-Free Shape Interpolation and Correspondence
• Semantic Foggy Scene Understanding with Synthetic Data
• U-Net: Convolutional Networks for Biomedical Image Segmentation

Cited by

• LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa

Related

• Worsening Perception: Real-time Degradation of Autonomous Vehicle Perception Performance for Simulation of Adverse Weather Conditions
• Bridging Clear and Adverse Driving Conditions
• SID: Stereo Image Dataset for Autonomous Driving in Adverse Conditions
• Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation
• Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather