Search papers, labs, and topics across Lattice.
This paper introduces AutoAWG, a novel framework for generating adverse weather videos to enhance the robustness of perception systems in autonomous driving. By employing a semantics-guided adaptive fusion of multiple controls and a vanishing point-anchored temporal synthesis strategy, AutoAWG achieves a significant reduction in the reliance on real-world data while maintaining high visual quality and annotation reusability. The framework demonstrates a 50% reduction in FID and a 16.1% reduction in FVD on the nuScenes validation set, highlighting its effectiveness in improving style fidelity and temporal consistency for downstream perception tasks.
AutoAWG cuts FID and FVD by up to 50% while generating high-fidelity adverse weather videos, revolutionizing data generation for autonomous driving.
Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to balance visual quality and annotation reusability. We present AutoAWG, a controllable Adverse Weather video Generation framework for Autonomous driving. Our method employs a semantics-guided adaptive fusion of multiple controls to balance strong weather stylization with high-fidelity preservation of safety-critical targets; leverages a vanishing point-anchored temporal synthesis strategy to construct training sequences from static images, thereby reducing reliance on synthetic data; and adopts masked training to enhance long-horizon generation stability. On the nuScenes validation set, AutoAWG significantly outperforms prior state-of-the-art methods: without first-frame conditioning, FID and FVD are relatively reduced by 50.0% and 16.1%; with first-frame conditioning, they are further reduced by 8.7% and 7.2%, respectively. Extensive qualitative and quantitative results demonstrate advantages in style fidelity, temporal consistency, and semantic--structural integrity, underscoring the practical value of AutoAWG for improving downstream perception in autonomous driving. Our code is available at: https://github.com/higherhu/AutoAWG