用合成数据训练自动驾驶3D检测模型，效果接近真实数据。
Synth It Like KITTI: Synthetic Data Generation for Object Detection in Driving Scenarios
- 基于CARLA仿真器生成带领域随机化的点云数据
- 在KITTI上实现接近真实数据的检测性能
- 小量真实数据微调即可媲美全量真实数据
推动自动驾驶系统发展的关键因素是仿真技术。然而，虚拟世界与现实世界之间的可迁移性仍进展有限。本文针对激光雷达点云上的3D目标检测问题重新审视该挑战，提出一种基于CARLA模拟器的数据生成流程。通过采用领域随机化策略并精细建模，我们仅使用合成数据训练目标检测器，并在KITTI数据集上验证其强大的泛化能力。此外，我们对比了不同虚拟传感器配置，分析导致域差距的关键传感器属性。最后，仅用少量真实数据微调即达到基线水平，使用全部真实数据训练时性能略有超越。
原文摘要 · Abstract (English)
An important factor in advancing autonomous driving systems is simulation. Yet, there is rather small progress for transferability between the virtual and real world. We revisit this problem for 3D object detection on LiDAR point clouds and propose a dataset generation pipeline based on the CARLA simulator. Utilizing domain randomization strategies and careful modeling, we are able to train an object detector on the synthetic data and demonstrate strong generalization capabilities to the KITTI dataset. Furthermore, we compare different virtual sensor variants to gather insights, which sensor attributes can be responsible for the prevalent domain gap. Finally, fine-tuning with a small portion of real data almost matches the baseline and with the full training set slightly surpasses it.
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。