结构到强度扩散的恶劣天气激光雷达生成
Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generation
把扩散去噪过程按「先几何结构、后反射强度」显式分解，并用真实传感器统计做天气退化仿真，可直接用于扩充恶劣天气下的激光雷达训练数据，也可作为点云生成中解耦几何与辐射属性的可复用范式。
原文依据 it first reconstructs the geometric structure, then conditions reflectance intensity denoising on the estimated structure
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论恶劣天气下的激光雷达点云生成受制于复杂天气所引发的退化。这些退化以根本不同的方式影响几何与反射率，使得联合建模困难且存在歧义，在多样化的真实训练数据有限时尤为如此。为解决这一问题，我们提出结构到强度扩散（SiD），一个基于扩散的框架，它在每个时间步上显式分解去噪过程：先重建几何结构，再以估计出的结构为条件对反射强度进行去噪。这种以结构为条件的设计分解了联合分布，降低了建模歧义，并生成在几何上连贯、在辐射上真实的点云。为缓解数据稀缺，我们引入真实先验天气仿真（RPWS），一个退化模块，利用真实世界的传感器统计量从清晰扫描中合成物理上合理的恶劣天气点云。大量实验表明，在相近的模型复杂度下，我们的方法在生成恶劣天气激光雷达扫描方面优于此前的最优方法，其结构与辐射属性都更贴近真实世界数据。
英文原文摘要 1253 字符
Adverse-weather LiDAR point cloud generation is challenged by complex weather-induced degradations. These degradations affect geometry and reflectance in fundamentally different ways, making joint modeling difficult and ambiguous, especially when diverse real-world training data is limited. To address this, we propose Structure-to-Intensity Diffusion (SiD), a diffusion-based framework that explicitly factorizes the denoising process at each time step: it first reconstructs the geometric structure, then conditions reflectance intensity denoising on the estimated structure. This structure-conditioned design decomposes the joint distribution, reduces modeling ambiguity, and leads to point clouds that are both geometrically coherent and radiometrically realistic. To mitigate data scarcity, we introduce Real-Prior Weather Simulation (RPWS), a degradation module that leverages real-world sensor statistics to synthesize physically plausible adverse-weather point clouds from clear scans. Extensive experiments demonstrate that, with similar model complexity, our approach outperforms the previous state-of-the-art in generating adverse-weather LiDAR scans with both structural and radiometric properties more closely aligned with real-world data.