GlobalMapper: Arbitrary-Shaped Urban Layout Generation
Liu He, Daniel Aliaga

TL;DR
GlobalMapper is a novel automatic method that uses graph attention networks to generate realistic and diverse urban building layouts from arbitrary road networks, supporting various city block shapes and building types.
Contribution
It introduces a fully automatic, graph attention network-based approach for urban layout generation that handles arbitrary city block shapes and supports conditional, diverse layout creation.
Findings
Outperforms prior layout generation methods in user studies
Supports arbitrary city block shapes and diverse building types
Successfully generates layouts for 28 large cities
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods
