Machine learning and complex compositional principles in architecture: Application of convolutional neural networks for generation of context-dependent spatial compositions

Dzieduszyński, Tomasz

doi:10.1177/14780771211066877

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An interesting approach to the analysis and construction of architectural compositions is presented by T. Dzieduszyński (2022). The author proposed a methodology for designing spatial compositions using digital technologies.…”

Section: Resultsmentioning

confidence: 99%

Untitled

2022

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Untitled

2022

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

The impact of new buildings on the city’s image

Koznarska¹,

Didyk²

2022

View full text Add to dashboard Cite

The research examines the visual perception of new buildings and their impact on changing the overall image of the city. Particular attention is devoted to buildings that are visible from other parts of the city due to their greater height and hilly terrain and can complement the overall composition of the city or destroy it. The importance of exploring the analysis of visual connections between the designed object and the environment is substantiated. The purpose of the research is to explore the perception of the city environment as a set of multifaceted pictures and to identify the elements that have a significant impact on the development of the overall image of the city. To achieve this purpose, a research methodology was developed, which at each stage included general scientific methods and special ones. Before starting the work, field research was conducted on the compositional structure of individual cities, and several paintings were selected for more detailed research. A compositional analysis of the selected examples for planning was conducted using the graphical method. It is established that the city’s image is most influenced by the last plan, which, in most cases, is not considered when designing new buildings. As a result of the research, the results obtained were verified for compliance with the shape, style and proportions of the newly built objects with the surrounding buildings. A significant number of paintings were identified that do not correspond to the expected result from the standpoint of the observer. Thus, there is a discrepancy between the planned and the received image of the overall compositional and spatial structure. The reasons for this inconsistency in the combination of individual plans are identified, which in turn had adverse effects on the overall image of the city. In addition, the main factors that influence the development of individual paintings have been identified. The result of the research is defined tasks for pre-design research at the initial stage of designing new buildings. This approach will help minimise mistakes in the design of new buildings, particularly those that have visual connections with other parts of the city and have a significant impact on the overall image

show abstract

Using Generative AI Midjourney to enhance divergent and convergent thinking in an architect’s creative design process

Tan,

Luhrs

2024

The Design Journal

View full text Add to dashboard Cite

Machine learning and complex compositional principles in architecture: Application of convolutional neural networks for generation of context-dependent spatial compositions

Cited by 4 publications

References 20 publications

Untitled

Untitled

The impact of new buildings on the city’s image

Using Generative AI Midjourney to enhance divergent and convergent thinking in an architect’s creative design process

Contact Info

Product

Resources

About