A Generative Urban Space Design Method Based on Shape Grammar and Urban Induction Patterns

Yang, Ling; Li, Jian; Chang, Hsiao-Tung; Zhao, Zhiqing; Ma, He; Zhou, Libin

doi:10.3390/land12061167

Cited by 6 publications

(3 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shape grammar, proposed in the 1970s [ 24 ], provides a formal framework for generating and analyzing complex shapes and designs. As as a shape-based visual description grammar and a rule-based automated design grammar, shape grammar has been applied to many domains, including urban planning [ 12 , 13 ], industrial design [ 14 ], and computer-aided design [ 15 ]. Over the years, advancements in shape grammar have led to the development of sophisticated methods for shape generation [ 25 ], analysis [ 26 ], and optimization [ 27 ], integrating computational techniques such as procedural modeling [ 19 ], parametric design [ 28 ], and machine learning [ 29 ].…”

Section: Related Workmentioning

confidence: 99%

“…Notably, techniques such as Variational Autoencoders (VAEs) [ 1 , 2 , 3 ], 3D Generative Adversarial Networks (3D-GANs) [ 4 , 5 , 6 ], and 3D Stable Diffusion [ 7 , 8 , 9 , 10 ] have shown promise in autonomously producing realistic and diverse 3D shapes. Shape grammars have also been demonstrated as a powerful approach for formal model generation by providing a rule-based framework for generating complex geometric structures and enforcing constraints within objects [ 11 , 12 , 13 ]. Each methodology has its advantages and limitations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bridging Formal Shape Models and Deep Learning: A Novel Fusion for Understanding 3D Objects

Zhang,

Willis

2024

Sensors

View full text Add to dashboard Cite

This article describes a novel fusion of a generative formal model for three-dimensional (3D) shapes with deep learning (DL) methods to understand the geometric structure of 3D objects and the relationships between their components, given a collection of unorganized point cloud measurements. Formal 3D shape models are implemented as shape grammar programs written in Procedural Shape Modeling Language (PSML). Users write PSML programs to describe complex objects, and DL networks estimate the configured free parameters of the program to generate 3D shapes. Users write PSML programs to enforce fundamental rules that define an object class and encode object attributes, including shapes, components, size, position, etc., into a parametric representation of objects. This fusion of the generative model with DL offers artificial intelligence (AI) models an opportunity to better understand the geometric organization of objects in terms of their components and their relationships to other objects. This approach allows human-in-the-loop control over DL estimates by specifying lists of candidate objects, the shape variations that each object can exhibit, and the level of detail or, equivalently, dimension of the latent representation of the shape. The results demonstrate the advantages of the proposed method over competing approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bridging Formal Shape Models and Deep Learning: A Novel Fusion for Understanding 3D Objects

Zhang,

Willis

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…. " Meanwhile, Yanbi praises the Black Tiger Spring as "Deep in the hollow of the cliff, the water is grey, and it seems that there is a real black tiger hiding there" in his poem "Seventy-two Springs" (Yu et al, 2018;Amado and Rodrigues, 2019;Liu et al, 2023;Yang et al, 2023). Additionally, the spiritual attributes of spatial arrangements serve as crucial foundations for the spirit of place.…”

Section: Analysis Of Spirit Of Place Values In Baihuazhou Historic Di...mentioning

confidence: 99%

Examining the urban regeneration of public cultural space using multi-scale geospatial data: a case study of the historic district in Jinan, China

Xu,

Tong,

Chen

et al. 2023

Front. Built Environ.

View full text Add to dashboard Cite

Introduction: Historical-cultural landscapes and urbanscapes integrate regional culture, collective memory, urban patterns, living habits, and other related historical and spatial information, and are important places for expressing the values of urban space. This study analyzes cultural landscapes and urbanscapes from the perspective of spatial values, taking the Baihuazhou historic and cultural district in Jinan as an example to analyze the spatial identification of public cultural space. The significance of this research lies in examining the urban regeneration of public cultural space using multi-scale geospatial data from both an objective and subjective perspective. This methdology is based on a large body of previous literature in relation to cultural heritage, and draws on a comprehensive understanding of the field.Methods: This study applies spatial syntax, visual graph, and survey analyses, focusing on urban spatial patterns, spatial culture, and spatial memory as heritage values.Results: The analysis results reveal that historic districts generally do not have good accessibility, predominantly because of the disorganized texture of the buildings and absence of spatial consistency.Discussion: There should be improved dynamic spatial identification and accessibility in older urban environments and enhancement of local spatial identification memory by increasing sightline accessibility. Based on consideration of values, corresponding suggestions are made from the three perspectives of urban space, cultural landscapes, and local collective memories to provide a reference for the protection of the Baihuazhou historic district and promote the preservation and development of similar heritage spaces.

show abstract

UDGAN: A new urban design inspiration approach driven by using generative adversarial networks

Gan,

Zhao,

Wang

et al. 2023

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

The morphological design of urban space affects the quality of the environment. The traditional experience-based design approach was greatly improved by introducing computational design tools. However, the existing urban design tools are mostly developed on pre-set rules or given targets, which have few contribution to enhance creativity or generate inspiring schemes. Therefore, this paper proposes a new computational urban design approach named UDGAN, integrating generative adversarial networks (GANs) and multi-objective optimization algorithms. This model utilize urban design scheme plans over the past 20 years from a particular designer as training datasets. Four preference models were trained to autonomously generate stylized urban design schemes. Eight morphological parameters were used to analyze the model performance by comparing generated results with the ground truth. This GAN-based surrogate approach is combined with a morphological indicator alignment process using multi-objective optimization model to obtain better results. The result shows that the r2 predicted by the improved Pix2Pix model reaches 0.798, and the similarity of the generated results can be stably distributed between 0.7-0.8, so the design scheme of this preferred style can be effectively learned. At the same time, the pre-trained model greatly reduces the time consumption of the design scheme generation, taking 5 min approximately to complete a generation process. This approach quickly generated the design scheme with preferred features, supporting the designer with creativity and greatly saving the time of design creation, transforming computational design into an inspiration-driven process.

show abstract

A Generative Urban Space Design Method Based on Shape Grammar and Urban Induction Patterns

Cited by 6 publications

References 23 publications

Bridging Formal Shape Models and Deep Learning: A Novel Fusion for Understanding 3D Objects

Bridging Formal Shape Models and Deep Learning: A Novel Fusion for Understanding 3D Objects

Examining the urban regeneration of public cultural space using multi-scale geospatial data: a case study of the historic district in Jinan, China

UDGAN: A new urban design inspiration approach driven by using generative adversarial networks

Contact Info

Product

Resources

About