让自动驾驶场景下雨更真实，雨量可调且多视角一致
GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes
- 用实测降雨数据建雨滴模型，结合几何感知扩散模型生成雨幕
- 雨强控制0-13mm/h，FID达149.09，优于现有方法
- 适合测试自动驾驶算法在可控雨天下的表现
现有自动驾驶场景降雨模拟方法在物理可控性和多视角一致性方面仍受限。本文提出GSRAIN，一种针对3D高斯泼溅（3DGS）驾驶场景的高低频降雨合成方法。该方法基于实测降雨数据构建高频雨滴模型，并利用几何感知单步扩散模型生成低频雨幕外观，二者在统一3DGS场景中融合，实现0–13 mm/h范围内的雨强可控。实验显示，该方法获得149.09的弗雷谢特初始距离（FID），优于CycleGAN-Turbo（155.71）和WeatherEdit（157.94）。目标检测与闭环驾驶实验表明，生成场景能揭示算法在不同降雨条件下的依赖性性能变化。结果表明，GSRAIN为自动驾驶提供了物理可控、可复现且支持闭环测试的雨天场景构建方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。