Realistic and diverse traffic scenarios in large quantities are crucial for the development and validation of autonomous driving systems. However, owing to numerous difficulties in the data collection process and the reliance on intensive annotations, real-world datasets lack sufficient quantity and diversity to support the increasing demand for data. This work introduces DriveSceneGen, a data-driven driving scenario generation method that learns from the real-world driving dataset and generates entire dynamic driving scenarios from scratch. DriveSceneGen is able to generate novel driving scenarios that align with real-world data distributions with high fidelity and diversity. Experimental results on 5k generated scenarios highlight the generation quality, diversity, and scalability compared to real-world datasets. To the best of our knowledge, DriveSceneGen is the first method that generates novel driving scenarios involving both static map elements and dynamic traffic participants from scratch.

翻译：大量逼真且多样化的交通场景对自动驾驶系统的开发与验证至关重要。然而，由于数据采集过程中的诸多困难以及对密集标注的依赖，真实世界数据集在数量和多样性上难以满足日益增长的数据需求。本文提出 DriveSceneGen——一种数据驱动的驾驶场景生成方法，该方法从真实驾驶数据集中学习，并从头生成完整的动态驾驶场景。DriveSceneGen 能够生成与真实数据分布高度一致的新颖驾驶场景，具备高保真度和多样性。在 5000 个生成场景上的实验结果凸显了其相较于真实数据集的生成质量、多样性和可扩展性。据我们所知，DriveSceneGen 是首个从头生成同时包含静态地图元素与动态交通参与者的新颖驾驶场景的方法。