用潜在扩散模型生成恶劣天气下的激光雷达场景，提升自动驾驶系统鲁棒性。
Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models
- 基于自编码器与潜在扩散模型，从晴天数据生成恶劣天气场景。
- 通过后处理增强生成场景的逼真度，提升真实感。
- 适合自动驾驶感知系统训练，尤其在数据稀缺的恶劣天气场景。
激光雷达场景是自动驾驶应用的基础数据源。尽管已有多个数据集，但恶劣天气条件下的场景仍十分稀少，限制了下游机器学习模型的鲁棒性，尤其影响自动驾驶系统在特定季节和地区的可靠性。由于季节限制，获取多样化的恶劣天气场景极具挑战。因此，生成模型尤为重要，可用于生成特定驾驶场景下的恶劣天气数据。本文提出一种由自编码器与潜在扩散模型构成的生成流程，并利用晴天激光雷达场景结合后处理步骤，提升生成恶劣天气场景的真实感。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。