{"slug": "fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog", "title": "FogDrive: A Multi-Modal Synthetic Driving Dataset for Perception under Graded Fog", "summary": "Researchers introduce FogDrive, a multi-modal synthetic driving dataset for autonomous driving under fog, containing 660 scenes (~133k frames) with four synchronized cameras, LiDAR, and radar across three calibrated fog densities (160m, 100m, 50m). Built with the CARLA simulator, the dataset achieves 95.1% annotation precision and over 99% recall for vehicles within 40m, and baseline benchmarks show that mixing multi-density fog during training improves 3D bounding-box geometry without added data-scaling cost. The dataset will be fully open-sourced to accelerate robust multi-modal research.", "body_md": "arXiv:2607.22698v1 Announce Type: new\nAbstract: Perception under adverse weather remains a critical bottleneck for reliable autonomous driving, yet existing benchmarks lack the systematic multi-modal alignments needed to evaluate robust sensor fusion. Real-world weather datasets suffer from uncontrolled collection and single-level, uncalibrated conditions, while synthetic alternatives either target camera-only restoration or lack the paired clean-and-foggy structure needed to benchmark \"defog-then-detect\" pipelines. We present FogDrive, a rigorously calibrated, multi-modal autonomous-driving dataset bridging data-centric engineering and robust machine learning. Built with the CARLA simulator, FogDrive contains 660 scenes (~133k fully annotated frames, 50:50 day/night) across four synchronized cameras (RGB, depth, semantic segmentation), a LiDAR and semantic-LiDAR pair, and front radar. Physically consistent fog is modeled independently on camera channels (Koschmieder model) and LiDAR channels (Beer-Lambert law) at three calibrated visibility densities (160m, 100m, 50m). Every scene ships in four matched variants (clean plus three graded fog levels) with cross-calibrated 2D and 3D bounding boxes. A semantic-segmentation-based quality audit over 8k images validates annotations at 95.1% precision and over 99% recall for vehicles within 40m. We establish baseline benchmarks with state-of-the-art architectures (TransFusion, BEVFusion, YOLOv8-m) across two paradigms: 3D multi-modal fusion and 2D image restoration. These yield critical data-centric insights: mixing multi-density fog during training tightens 3D bounding-box geometry without added data-scaling cost, while in 2D pipelines image-quality metrics (PSNR, SSIM) prove poor predictors of downstream detection performance. FogDrive will be fully open-sourced alongside our data-generation framework to accelerate robust, multi-modal research.", "url": "https://wpnews.pro/news/fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog", "canonical_source": "https://arxiv.org/abs/2607.22698", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 04:07:58.195316+00:00", "lang": "en", "topics": ["autonomous-vehicles", "computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["FogDrive", "CARLA simulator", "TransFusion", "BEVFusion", "YOLOv8-m"], "alternates": {"html": "https://wpnews.pro/news/fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog", "markdown": "https://wpnews.pro/news/fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog.md", "text": "https://wpnews.pro/news/fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog.txt", "jsonld": "https://wpnews.pro/news/fogdrive-a-multi-modal-synthetic-driving-dataset-for-perception-under-graded-fog.jsonld"}}