Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Exploring urban forms using deep generative models based on topology

Lin, Bo 2022. Exploring urban forms using deep generative models based on topology. PhD Thesis, Cardiff University.
Item availability restricted.

[thumbnail of thesis-submission-version-no-signatures.pdf]
Preview
PDF - Accepted Post-Print Version
Download (9MB) | Preview
[thumbnail of Cardiff University Electronic Publication Form] PDF (Cardiff University Electronic Publication Form) - Supplemental Material
Restricted to Repository staff only

Download (176kB)

Abstract

Integrating deep generative models into urban form generation is an innovative and promising approach to support the urban design process. However, most urban form generation approaches assisted by deep generative models consider image-based representations of urban form, neglecting the overall topological information among streets, blocks, and buildings. This research aims to support urban design in the early stages through deep generative models based on topology. The developed framework can provide multiple design solutions for urban designers in the early stage of urban design and support the urban design process. There are seven parts to this research. Firstly, the introduction of the research is presented. Secondly, this research reviews urban form generation, from artificial intelligence (AI) to deep generative models, and state of the art. Thirdly, the research methodology is presented. Fourthly, a survey is conducted to understand the user acceptance and visions of professionals, academics, and students in the field of architecture and urban design towards the application of deep generative models in architectural and urban form generation. Fifthly, the topology-based urban form generation framework aided by deep generative models is proposed. Sixthly, the street network generation based on topology using deep generative models is developed and validated. Seventhly, the building configuration generation based on topology using deep generative models is developed and validated. Eighthly, the research results are discussed, and the conclusion of the research is presented.

Item Type: Thesis (PhD)
Date Type: Completion
Status: Unpublished
Schools: Architecture
Date of First Compliant Deposit: 26 April 2023
Last Modified: 26 Apr 2024 01:30
URI: https://orca.cardiff.ac.uk/id/eprint/159058

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics