On the Role of Representations for Reasoning in Large-Scale Urban Scenes

Randi Cabezas, Maros Blaha, Sue Zheng, Guy Rosman, Konrad Schindler, John W. Fisher III; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 29-38

The advent of widely available photo collections covering broad geographic areas has spurred significant advances in large-scale urban scene modeling. While much emphasis has been placed on reconstruction and visualization, the utility of such models extends well beyond. Specifically, these models should support a wide variety of reasoning tasks (or queries), and thus enable advanced scene study. Driven by this interest, we analyze 3D representations for their utility to perform queries. Since representations as well as queries are highly heterogeneous, we build on a categorization that serves as a coupling interface between both domains. Equipped with our taxonomy and the notion of uncertainty in the representation, we quantify the utility of representations for solving three archetypal reasoning tasks in terms of accuracy, uncertainty and computational complexity. We provide an empirical analysis of these intertwined realms on challenging real and synthetic urban scenes.