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

• URL: http://arxiv.org/abs/2608.02177v1
• Date: Mon, 03 Aug 2026 12:57:44 GMT
• Title: GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes
• Abstract summary: GSRAIN is a high-/low-frequency rainfall synthesis method for 3D Gaussian Splatting (3DGS) driving scenes.<n>The proposed method achieves a Fréchet Inception Distance (FID) of 149.09, outperforming CycleGAN-Turbo (155.71) and WeatherEdit (157.94)
• Score: 5.239786600452129
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• Raindrop GS: A Benchmark for 3D Gaussian Splatting under Raindrop Conditions [23.642500549050027]
  RaindropGS is a benchmark designed to evaluate the full 3DGS pipeline-from unconstrained, raindrop-corrupted images to clear 3DGS reconstructions.<n>First, we collect a real-world raindrop reconstruction dataset, in which each scene contains three aligned image sets.<n>Through comprehensive experiments and analyses, we reveal critical insights into the performance limitations of existing 3DGS methods on unconstrained raindrop images.
  arXiv  Detail & Related papers  (2025-10-20T16:36:15Z)
• Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining [73.5575992346396]
  We propose a dual-branch-temporal state-space model to enhance rain streak removal in video sequences.<n>To improve multi-frame feature fusion, we derive a dynamic filter stacking, which adaptively approximates statistical filters for pixel-wise feature refinement.<n>To further explore the capacity of deraining models in supporting other vision-based tasks in rainy environments, we introduce a novel real-world benchmark.
  arXiv  Detail & Related papers  (2025-05-22T15:50:00Z)
• PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining [47.81253972389206]
  Event cameras excel in high temporal resolution and dynamic range but suffer from dense noise in rainy conditions.<n>We propose PRE-Mamba, a novel point-based camera framework for event deraining.
  arXiv  Detail & Related papers  (2025-05-08T14:52:45Z)
• DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments [4.86090922870914]
  This study introduces the novel task of 3D Reconstruction in Rainy Environments (3DRRE) To benchmark this task, we construct the HydroViews dataset that comprises a diverse collection of both synthesized and real-world scene images. We propose DeRainGS, the first 3DGS method tailored for reconstruction in adverse rainy environments.
  arXiv  Detail & Related papers  (2024-08-21T11:39:18Z)
• TRG-Net: An Interpretable and Controllable Rain Generator [61.2760968459789]
  This study proposes a novel deep learning based rain generator, which fully takes the physical generation mechanism underlying rains into consideration. Its significance lies in that the generator not only elaborately design essential elements of the rain to simulate expected rains, but also finely adapt to complicated and diverse practical rainy images. Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks.
  arXiv  Detail & Related papers  (2024-03-15T03:27:39Z)
• Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection [26.278415287992964]
  Previous research has attempted to address this by simulating the noise from rain to improve the robustness of detection models. We propose a novel rain simulation method, termed DRET, that unifies Dynamics and Rainy Environment Theory. We also present a Sunny-to-Rainy Knowledge Distillation approach to enhance 3D detection under rainy conditions.
  arXiv  Detail & Related papers  (2024-02-28T17:21:02Z)
• Challenges of YOLO Series for Object Detection in Extremely Heavy Rain: CALRA Simulator based Synthetic Evaluation Dataset [0.0]
  Object detection by diverse sensors (e.g., LiDAR, radar, and camera) should be prioritized for autonomous vehicles. These sensors require to detect objects accurately and quickly in diverse weather conditions, but they tend to have challenges to consistently detect objects in bad weather conditions with rain, snow, or fog. In this study, based on experimentally obtained raindrop data from precipitation conditions, we constructed a novel dataset that could test diverse network model in various precipitation conditions.
  arXiv  Detail & Related papers  (2023-12-13T08:45:57Z)
• Hierarchical-level rain image generative model based on GAN [4.956959291938016]
  hierarchical-level rain image generative model, rain conditional CycleGAN, is constructed. Different rain intensities are introduced as labels in conditional GAN. Model structure is optimized and the training strategy is adjusted to alleviate the problem of mode collapse.
  arXiv  Detail & Related papers  (2023-09-06T12:59:52Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)
• Semi-Supervised Video Deraining with Dynamic Rain Generator [59.71640025072209]
  This paper proposes a new semi-supervised video deraining method, in which a dynamic rain generator is employed to fit the rain layer. Specifically, such dynamic generator consists of one emission model and one transition model to simultaneously encode the spatially physical structure and temporally continuous changes of rain streaks. Various prior formats are designed for the labeled synthetic and unlabeled real data, so as to fully exploit the common knowledge underlying them.
  arXiv  Detail & Related papers  (2021-03-14T14:28:57Z)
• From Rain Generation to Rain Removal [67.71728610434698]
  We build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator. We employ the variational inference framework to approximate the expected statistical distribution of rainy image. Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution.
  arXiv  Detail & Related papers  (2020-08-08T18:56:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.