A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Imaging Place Using Generative Adversarial Networks (GAN Loci)
This chapter applies techniques in machine learning, specifically generative adversarial networks (GANs), to produce synthetic images intended to capture the predominant visual properties of urban places. It proposes that imaging cities in this manner represents the first computational approach to documenting the genius loci of a city, which is understood to include those forms, textures, colours, and qualities of light that exemplify a particular urban location and that set it apart from similar places. The chapter includes methods for the collection of urban image data, for the necessary processing and formatting of these data, and for the training of two known computational statistical models that identify visual patterns distinct to a given site and that reproduce these patterns to generate new images. It describes the steps required to train a GAN to produce images that capture the predominant visual properties of an urban context.
Imaging Place Using Generative Adversarial Networks (GAN Loci)
This chapter applies techniques in machine learning, specifically generative adversarial networks (GANs), to produce synthetic images intended to capture the predominant visual properties of urban places. It proposes that imaging cities in this manner represents the first computational approach to documenting the genius loci of a city, which is understood to include those forms, textures, colours, and qualities of light that exemplify a particular urban location and that set it apart from similar places. The chapter includes methods for the collection of urban image data, for the necessary processing and formatting of these data, and for the training of two known computational statistical models that identify visual patterns distinct to a given site and that reproduce these patterns to generate new images. It describes the steps required to train a GAN to produce images that capture the predominant visual properties of an urban context.
Imaging Place Using Generative Adversarial Networks (GAN Loci)
Carta, Silvio (editor) / Steinfeld, Kyle (author)
Machine Learning and the City ; 513-516
2022-05-21
4 pages
Article/Chapter (Book)
Electronic Resource
English
Generative adversarial networks in construction applications
| Elsevier | 2024
Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks
| Springer Verlag | 2024