用3D生成自动化构建高保真驾驶数据，解决真实场景难采集问题
SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
- 基于3D生成自动挖掘与创建虚拟资产和罕见场景
- 支持通用物体类别，突破仅限车辆的局限
- 适合自动驾驶感知模型训练与稀有场景增强
在自动驾驶领域，传感器仿真对于生成现实世界难以捕获的罕见且多样化场景至关重要。现有方法分为两类：1）基于计算机图形（CG）的方法，如CARLA，缺乏多样性且难以扩展至大量罕见案例；2）基于学习的方法，如NeuSim，仅适用于特定物体类别（如车辆），且需大量多传感器数据，限制了其在通用物体上的应用。为解决上述局限，我们提出一个可扩展的real2sim2real系统，利用3D生成技术实现资产挖掘、生成与罕见场景数据合成的自动化。
原文摘要 · Abstract (English)
In the field of autonomous driving, sensor simulation is essential for generating rare and diverse scenarios that are difficult to capture in real-world environments. Current solutions fall into two categories: 1) CG-based methods, such as CARLA, which lack diversity and struggle to scale to the vast array of rare cases required for robust perception training; and 2) learning-based approaches, such as NeuSim, which are limited to specific object categories (vehicles) and require extensive multi-sensor data, hindering their applicability to generic objects. To address these limitations, we propose a scalable real2sim2real system that leverages 3D generation to automate asset mining, generation, and rare-case data synthesis.
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。