Navigation using special buildings as signposts

Navigation has been greatly improved by positioning systems, but visualization still relies on maps. Yet because they only represent an abstract street network, maps are sometimes difficult to read. Conversely, Tourist Maps, which are enriched with landmark drawings, have been shown to be much more intuitive to understand. However, outside the very centres of cities, major landmarks are too sparse to be helpful. In this work, we present a method to automatically augment maps with most locally prominent such buildings, at multiple scale. Further, we generate a characterization which helps emphasize the special attributes of these buildings. Descriptive features are extracted from facades, analyzed and re-ranked to match human perception. To do so, we collected a total number of over 5900 human annotations to characterize 117 facades across 3 different cities. Finally, the characterizations are also used to produce natural language descriptions of the facades.