FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs

TL;DR

FrankenGAN is a cascade of style-synchronized GANs that automatically adds realistic, semantically consistent details and textures to coarse building models, enabling large-scale, controllable urban detail synthesis.

Contribution

We introduce FrankenGAN, a novel multi-scale GAN framework that generates style-consistent, detailed building textures and geometry with user-controlled variability for urban modeling.

Findings

Generated details are realistic and semantically plausible.

Outputs are style-consistent across large neighborhoods.

User controls effectively influence style variability.

Abstract

Coarse building mass models are now routinely generated at scales ranging from individual buildings through to whole cities. For example, they can be abstracted from raw measurements, generated procedurally, or created manually. However, these models typically lack any meaningful semantic or texture details, making them unsuitable for direct display. We introduce the problem of automatically and realistically decorating such models by adding semantically consistent geometric details and textures. Building on the recent success of generative adversarial networks (GANs), we propose FrankenGAN, a cascade of GANs to create plausible details across multiple scales over large neighborhoods. The various GANs are synchronized to produce consistent style distributions over buildings and neighborhoods. We provide the user with direct control over the variability of the output. We allow her to interactively specify style via images and manipulate style-adapted sliders to control style variability. We demonstrate our system on several large-scale examples. The generated outputs are qualitatively evaluated via a set of user studies and are found to be realistic, semantically-plausible, and style-consistent.