Abstract

We present a fast, simple location recognition and image localization method that leverages feature correspondence and geometry estimated from large Internet photo collections. Such recovered structure contains a signi ficant amount of useful information about images and image features that is not available when considering images in isolation. For instance, we can predict which views will be the most common, which feature points in a scene are most reliable, and which features in the scene tend to co-occur in the same image. Based on this informa- tion, we devise an adaptive, prioritized algorithm for matching a representative set of SIFT features covering a large scene to a query image for efficient local- ization. Our approach is based on considering features in the scene database, and matching them to query image features, as opposed to more conventional meth- ods that match image features to visual words or database features. We find this approach results in improved performance, due to the richer knowledge of char- acteristics of the database features compared to query image features. We present experiments on two large city-scale photo collections, showing that our algorithm compares favorably to image retrieval-style approaches to location recognition.