Atmospheric visibility is an important and complex meteorological variable that directly affects safe and reliable transportation. Specifically, declining visibility can pose an increased risk to automotive, aviation, and maritime traffic and operations. Traditional visibility sensors, e.g., those of the Automated Surface Observing Systems (ASOS) network, are costly and designed for air traffic use, thus these visibility sensor networks have limited coverage state-wide. In contrast, camera footage is highly available, accessible, and fairly inexpensive. While it is possible to construct a model that detects a visibility measure for a single camera or location, this type of model is not generalizable to new locations with varying physical features or different fields of view. I propose a comparative visibility model that is generalizable solution to new locations. I train a convolutional neural network (CNN) that compares a query image and a reference image that originate from the same camera, and determines the degree to which the query image is less visible than the reference image. A query image from a new camera can then be compared to a set of reference images with known visibility distances from the same camera. These comparisons can then be used to infer the query image’s underlying visibility distance. In addition, a model can be trained using a set of locations that have different maximum visibility distances, fields of view, and physical characteristics. The resulting comparative model can generalize to novel sites. When combined with a small number of calibrated reference images for a given site, visibility distances can be accurately estimated from previously unseen query images. Results from a large combined NYSM/ASOS data set show that the models learned using the proposed method are able to generalize to new locations. The approach is successful in the comparative case and the numerical visibility prediction case. With these outcomes, the model is also able to effectively monitor visibility over time.