Building LiDAR generative models holds promise as powerful data priors for restoration, scene manipulation, and scalable simulation in autonomous mobile robots. In recent years, approaches using diffusion models have emerged, significantly improving training stability and generation quality. Despite the success of diffusion models, generating high-quality samples requires numerous iterations of running neural networks, and the increasing computational cost can pose a barrier to robotics applications. To address this challenge, this paper presents R2Flow, a fast and high-fidelity generative model for LiDAR data. Our method is based on rectified flows that learn straight trajectories, simulating data generation with much fewer sampling steps against diffusion models. We also propose a efficient Transformer-based model architecture for processing the image representation of LiDAR range and reflectance measurements. Our experiments on the unconditional generation of the KITTI-360 dataset demonstrate the effectiveness of our approach in terms of both efficiency and quality.

翻译：构建激光雷达生成模型有望为自主移动机器人的数据恢复、场景操控和可扩展仿真提供强大的数据先验。近年来，基于扩散模型的方法逐渐兴起，显著提升了训练稳定性和生成质量。尽管扩散模型取得了成功，但生成高质量样本需要进行大量神经网络迭代运算，日益增长的计算成本可能成为机器人应用中的障碍。为应对这一挑战，本文提出了R2Flow——一种面向激光雷达数据的快速高保真生成模型。该方法基于学习直线轨迹的整流流，能以远少于扩散模型的采样步数模拟数据生成过程。我们还提出了一种高效的基于Transformer的模型架构，用于处理激光雷达测距与反射强度测量的图像表征。在KITTI-360数据集上的无条件生成实验表明，我们的方法在效率与质量方面均展现出显著优势。