mlsanityData to 14 Oct 2026

GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes

arXiv 2608.02177 ↗First posted 3 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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'echet 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

38 of 50 references.

References · 38

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  6. 2022Planning-oriented Autonomous Drivingcited by 1,087
  7. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  8. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  9. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 360
  10. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 297
  11. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 290
  12. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 261
26 more
  1. 2024DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generationcited by 191
  2. 2024OmniRe: Omni Urban Scene Reconstructioncited by 161
  3. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 150
  4. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  5. 2024One-Step Image Translation with Text-to-Image Modelscited by 116
  6. 2023Street-View Image Generation from a Bird's-Eye View Layoutcited by 102
  7. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 90
  8. 2025YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detectioncited by 79
  9. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
  10. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  11. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 58
  12. 2020Rain rendering for evaluating and improving robustness to bad weathercited by 57
  13. 2024AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstructioncited by 52
  14. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  15. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 38
  16. 2021Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translationcited by 36
  17. 2024SGSST: Scaling Gaussian Splatting StyleTransfercited by 20
  18. 2024HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenescited by 16
  19. 2025RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splattingcited by 13
  20. 2024PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Modelscited by 12
  21. 2025WeatherEdit: Controllable Weather Editing with 4D Gaussian Fieldcited by 12
  22. 2025StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussianscited by 6
  23. 2025Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Modelscited by 4
  24. 2025FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splattingcited by 3
  25. 2026Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splattingcited by 2
  26. 2025Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards
  2. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
  3. 2025Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation
  4. 2024SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
  5. 2026RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models
  6. 2026Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
  7. 2026Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
  8. 2024Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection