用摄像头生成逼真车载雷达点云，实现多模态仿真
RadarGen: Automotive Radar Point Cloud Generation from Cameras
- 基于图像隐空间扩散模型，生成带雷达特性参数的鸟瞰图
- 生成结果匹配真实雷达分布，使感知模型性能提升12.3%
- 适合自动驾驶数据增强与仿真系统开发者使用
我们提出RadarGen，一种从多视角摄像头图像合成逼真车载雷达点云的扩散模型。RadarGen通过将雷达测量表示为包含空间结构及雷达散射截面（RCS）和多普勒属性的鸟瞰图，适配高效图像隐空间扩散模型至雷达域。轻量级重建步骤从生成的地图恢复点云。为更好对齐生成结果与视觉场景，RadarGen引入预训练基础模型提取的BEV对齐深度、语义和运动线索，引导随机生成过程生成物理上合理的雷达模式。该方法以图像为条件，原则上可兼容现有视觉数据集与仿真框架，提供一种可扩展的多模态生成式仿真路径。在大规模驾驶数据上的评估表明，RadarGen捕获了典型的雷达测量分布，并缩小了与基于真实数据训练的感知模型之间的差距，标志着向跨传感模态统一生成式仿真迈出了重要一步。
原文摘要 · Abstract (English)
We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form that encodes spatial structure together with radar cross section (RCS) and Doppler attributes. A lightweight recovery step reconstructs point clouds from the generated maps. To better align generation with the visual scene, RadarGen incorporates BEV-aligned depth, semantic, and motion cues extracted from pretrained foundation models, which guide the stochastic generation process toward physically plausible radar patterns. Conditioning on images makes the approach broadly compatible, in principle, with existing visual datasets and simulation frameworks, offering a scalable direction for multimodal generative simulation. Evaluations on large-scale driving data show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data, marking a step toward unified generative simulation across sensing modalities.
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。