发表机构
College of Automotive and Energy Engineering, Tongji University（同济大学汽车与能源工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GSRAIN针对自动驾驶降雨模拟的物理可控性与多视图一致性局限，结合实测数据与几何感知扩散模型生成可控降雨场景，在FID指标上优于现有方法，可用于自动驾驶算法的雨天测试。
AI 中文摘要
现有自动驾驶的降雨模拟方法在物理可控性和多视图一致性方面仍存在局限。本文提出GSRAIN，一种面向3D高斯溅射（3DGS）驾驶场景的高低频降雨合成方法。GSRAIN利用实测降雨数据构建高频雨滴模型，采用几何感知单步扩散模型生成低频降雨外观，随后将两种效果融合至统一的3DGS场景，可实现0至13mm/h范围内的降雨强度控制。该方法取得了149.09的Fréchet Inception Distance（FID），优于CycleGAN-Turbo（155.71）和WeatherEdit（157.94）。目标检测与闭环驾驶实验进一步表明，生成的场景可展现评估算法在可控降雨下的场景依赖性能变化。这些结果显示，GSRAIN为构建物理可控、可重复且兼容闭环的自动驾驶雨天测试场景提供了有效途径。
英文摘要
Existing rainfall simulation methods for autonomous driving remain limited in physical controllability and multi-view consistency. This paper presents GSRAIN, a high-/low-frequency rainfall synthesis method for 3D Gaussian Splatting (3DGS) driving scenes. GSRAIN constructs a high-frequency raindrop model from measured rainfall data and generates low-frequency rainy appearance using a geometry-aware single-step diffusion model. The two effects are then fused in a unified 3DGS scene, enabling rainfall-intensity control over the range of 0--13~mm/h. The proposed method achieves a Fréchet Inception Distance (FID) of 149.09, outperforming CycleGAN-Turbo (155.71) and WeatherEdit (157.94). Object-detection and closed-loop driving experiments further show that the generated scenes expose scene-dependent performance changes of the evaluated algorithms under controllable rainfall. These results indicate that GSRAIN provides an effective approach for constructing physically controllable, repeatable, and closed-loop-compatible rainy-weather test scenes for autonomous driving.
