Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots, such as scalable simulation, scene manipulation, and sparse-to-dense completion of LiDAR point clouds. While existing approaches have demonstrated the feasibility of image-based LiDAR data generation using deep generative models, they still struggle with fidelity and training stability. In this work, we present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds based on the image representation of range and reflectance intensity. Our method is built upon denoising diffusion probabilistic models (DDPMs), which have shown impressive results among generative model frameworks in recent years. To effectively train DDPMs in the LiDAR domain, we first conduct an in-depth analysis of data representation, loss functions, and spatial inductive biases. Leveraging our R2DM model, we also introduce a flexible LiDAR completion pipeline based on the powerful capabilities of DDPMs. We demonstrate that our method surpasses existing methods in generating tasks on the KITTI-360 and KITTI-Raw datasets, as well as in the completion task on the KITTI-360 dataset. Our project page can be found at https://kazuto1011.github.io/r2dm.

翻译：三维激光雷达数据的生成建模是一项新兴任务，在自主移动机器人领域具有广阔应用前景，例如可扩展仿真、场景操控以及激光雷达点云的稀疏到稠密补全。尽管现有方法已证明利用深度生成模型进行基于图像的激光雷达数据生成的可行性，但其在保真度和训练稳定性方面仍存在不足。本文提出R2DM——一种新颖的激光雷达数据生成模型，能够基于距离与反射率强度的图像表示生成多样化且高保真的三维场景点云。该方法建立在去噪扩散概率模型（DDPMs）基础上，该模型近年来在生成模型框架中展现出卓越性能。为在激光雷达领域有效训练DDPMs，我们首先对数据表示、损失函数和空间归纳偏置进行了深入分析。借助R2DM模型，我们还基于DDPMs的强大能力引入了一种灵活的激光雷达补全流程。实验证明，在KITTI-360和KITTI-Raw数据集上的生成任务以及KITTI-360数据集上的补全任务中，我们的方法均超越了现有方法。项目页面详见https://kazuto1011.github.io/r2dm。