Clear Weather is a dataset for object detection in challenging weather conditions. The dataset includes 12,000 samples from real-world driving scenarios and 1,500 samples from controlled weather conditions in a fog chamber. The dataset includes accurate 2D and 3D bounding box annotations for a total of 100,000 objects in different weather conditions such as fog, snow, and rain. The dataset provides a testing ground for a wide range of algorithms for signal enhancement, domain adaptation, object detection, or multimodal sensor fusion with a focus on learning robust redundancy between sensors.