Multi-Sensor Alignment for Weather Simulations

• URL: http://arxiv.org/abs/2607.25612v1
• Date: Tue, 28 Jul 2026 11:43:17 GMT
• Title: Multi-Sensor Alignment for Weather Simulations
• Abstract summary: Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions.<n>To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors.<n>We propose the Reference dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit) for particle positioning alignment in rain and snow.
• Score: 1.9021908527898033
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions. Due to lack of real-world weather datasets, weather simulations are a promising alternative. To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors. To achieve this, we propose the Reference Dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit[1]) for particle positioning alignment in rain and snow. We validate both alignment methods using statistical and geometrical tests, respectively. We find that 3D detection models for non-aligned versions tend to be overly optimistic as compared to aligned versions. We also show the aligned-multi-sensor simulation's effectiveness for achieving robustness for 3D object detection task by finetuning existing sensor fusion models on it.

Related papers

• Controllable Weather Synthesis and Removal with Video Diffusion Models [61.56193902622901]
  WeatherWeaver is a video diffusion model that synthesizes diverse weather effects directly into any input video.<n>Our model provides precise control over weather effect intensity and supports blending various weather types, ensuring both realism and adaptability.
  arXiv  Detail & Related papers  (2025-05-01T17:59:57Z)
• DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness [79.4785166021062]
  Most 3D object generators prioritize aesthetic quality, often neglecting the physical constraints necessary for practical applications.<n>Previous approaches to generating stable 3D objects relied on differentiable physics simulators to optimize geometry at test time.<n>This framework leverages feedback from a (non-differentiable) simulator to increase the likelihood that the 3D generator directly outputs stable 3D objects.
  arXiv  Detail & Related papers  (2025-03-28T17:59:53Z)
• MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection [22.277210748714378]
  Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. Experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection.
  arXiv  Detail & Related papers  (2024-07-23T12:58:49Z)
• 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)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• LiDAR Snowfall Simulation for Robust 3D Object Detection [116.10039516404743]
  We propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds. Our method samples snow particles in 2D space for each LiDAR line and uses the induced geometry to modify the measurement for each LiDAR beam. We use our simulation to generate partially synthetic snowy LiDAR data and leverage these data for training 3D object detection models that are robust to snowfall.
  arXiv  Detail & Related papers  (2022-03-28T21:48:26Z)
• Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather [92.84066576636914]
  This work addresses the challenging task of LiDAR-based 3D object detection in foggy weather. We tackle this problem by simulating physically accurate fog into clear-weather scenes. We are the first to provide strong 3D object detection baselines on the Seeing Through Fog dataset.
  arXiv  Detail & Related papers  (2021-08-11T14:37:54Z)
• 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)

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.