LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed under single-domain settings, requiring separate models for different datasets or sensing conditions and hindering unified, controllable synthesis under heterogeneous distribution shifts. To this end, we present OmniLiDAR, a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains spanning three shift types: adverse weather, sensor-configuration changes (e.g., reduced beams), and cross-platform acquisition (vehicle, drone, and quadruped). To enable training a single model over heterogeneous domains without isolating optimization by domain, we introduce a Cross-Domain Training Strategy (CDTS) that mixes domains within each mini-batch and leverages conditioning to steer generation. We further propose Cross-Domain Feature Modeling (CDFM), which captures directional dependencies along azimuth and elevation axes to reflect the anisotropic scanning structure of range images, and Domain-Adaptive Feature Scaling (DAFS) as a lightweight modulation to account for structured domain-dependent feature shifts during denoising. In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction while following official splits. Extensive experiments demonstrate strong generation fidelity and consistent gains in downstream use cases, including generative data augmentation for LiDAR semantic segmentation and 3D object detection, as well as robustness evaluation under corruptions, with consistent benefits in limited-label regimes.

翻译：激光雷达场景生成对于可扩展仿真和合成数据创建日益重要，尤其是在多样化的传感条件下——这些条件难以大规模采集。通常，基于扩散的激光雷达生成器是在单域设置下开发的，需要针对不同数据集或传感条件建立独立模型，这阻碍了异构分布偏移下的统一可控合成。为此，我们提出OmniLiDAR，这是一个统一的文本条件扩散框架，能够在跨八种代表性域（涵盖三种偏移类型：恶劣天气、传感器配置变化（如减少扫描线数）、跨平台采集（车辆、无人机、四足机器人））的共享距离图像表示中生成激光雷达扫描。为实现在异构域上训练单一模型而无需按域隔离优化，我们引入跨域训练策略（CDTS），该策略在每个小批量内混合不同域，并利用条件引导生成。我们进一步提出跨域特征建模（CDFM），用于捕捉沿方位角和仰角轴的方向依赖性，以反映距离图像的各向异性扫描结构；以及域自适应特征缩放（DAFS），作为一种轻量级调制机制，用于在去噪过程中考虑结构化域相关特征偏移。鉴于缺乏公开统一基准，我们通过结合真实扫描、基于物理的天气模拟和系统性扫描线减少，并遵循官方数据划分方式，构建了一个八域数据集。大量实验表明，该方法在生成保真度方面表现优异，并在下游应用中持续取得性能提升，包括用于激光雷达语义分割和三维目标检测的生成式数据增强，以及在损坏条件下的鲁棒性评估，同时在标签有限场景下带来一致收益。