Research Data Leeds Repository

FrankenGAN Powerpoint presentation

Kelly, Tom and Guerrero, Paul (2019) FrankenGAN Powerpoint presentation. University of Leeds. [Dataset] https://doi.org/10.5518/608

Dataset description

Powerpoint presentation from Siggraph Asia (Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia) 2018, including 3D models and animation.

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.

Keywords: generative adversarial networks, urban modeling, computer graphics
Divisions: Faculty of Engineering > School of Computing
Related resources:
LocationType
https://vcg.leeds.ac.uk/projects/frankengan/Website
https://doi.org/10.1145/3272127.3275065Publication
https://github.com/twak/chordatlasSoftware
https://github.com/twak/bikeganSoftware
https://web.archive.org/web/20190814135633/https://sa2018.siggraph.org/en/Website
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Date deposited: 18 Nov 2019 15:30
URI: http://archive.researchdata.leeds.ac.uk/id/eprint/605

Files

Data

Research Data Leeds Repository is powered by EPrints
Copyright © 2021 University of Leeds