Enhancing Rural Autonomous Driving Performance with Diffusion-Augmented Synthetic Datasets

Synthetic datasets are increasingly used to train autonomous vehicle (AV) models, providing large-scale, diverse, and realistic data for perception and decision-making tasks. However, their predominant focus on urban environments limits effectiveness in rural areas, creating potential safety risks, while collecting real-world rural driving data remains time-consuming and costly. In this work, we leverage diffusion models to enhance the realism of synthetic driving data, focusing on features critical to rural navigating such as curves, hills, and varied terrain. Quantitative metrics and qualitative evaluations demonstrate that diffusion-enhanced datasets improve the robustness and reliability of AV models in underrepresented rural scenarios. Our results show statistically significant improvements over both heuristic baselines and real-world trained models, highlighting the scalability of diffusion-based synthetic data to cover rare but critical driving situations.