GlobalMapper: Arbitrary-Shaped Urban Layout Generation
This addresses the need for automated urban layout design in computer vision, graphics, and urban applications, offering a novel method for arbitrary-shaped city blocks.
The paper tackles the problem of generating realistic urban building layouts from arbitrary road networks by proposing a fully automatic approach using graph attention networks, achieving superior performance compared to prior methods as demonstrated in a user study and by generating layouts for 28 large cities.
Modeling and designing urban building layouts is of significant interest in computer vision, computer graphics, and urban applications. A building layout consists of a set of buildings in city blocks defined by a network of roads. We observe that building layouts are discrete structures, consisting of multiple rows of buildings of various shapes, and are amenable to skeletonization for mapping arbitrary city block shapes to a canonical form. Hence, we propose a fully automatic approach to building layout generation using graph attention networks. Our method generates realistic urban layouts given arbitrary road networks, and enables conditional generation based on learned priors. Our results, including user study, demonstrate superior performance as compared to prior layout generation networks, support arbitrary city block and varying building shapes as demonstrated by generating layouts for 28 large cities.