GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes
Abstract
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 Fr\'{e}chet 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.
Keywords
Cite
@article{arxiv.2608.02177,
title = {GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes},
author = {Fanyu Wang and Longgao Zhang and Junyi Chen},
journal= {arXiv preprint arXiv:2608.02177},
year = {2026}
}