Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models
This addresses the problem of limited robustness in autonomous driving systems due to seasonal data gaps, though it is incremental as it builds on existing generative methods.
The paper tackles the scarcity of LiDAR scenes in adverse weather conditions for autonomous driving by proposing a latent diffusion model with autoencoder and postprocessing, achieving improved realism in generated scenes.
LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rarely available. This limits the robustness of downstream machine learning models, and restrains the reliability of autonomous driving systems in particular locations and seasons. Collecting feature-diverse scenes under adverse weather conditions is challenging due to seasonal limitations. Generative models are therefore essentials, especially for generating adverse weather conditions for specific driving scenarios. In our work, we propose a latent diffusion process constituted by autoencoder and latent diffusion models. Moreover, we leverage the clear condition LiDAR scenes with a postprocessing step to improve the realism of the generated adverse weather condition scenes.