id |
ecaade2024_29 |
authors |
Brama, Haya; Dalach, Agata; Grinshpoun, Tal; Dortheimer, Jonathan |
year |
2024 |
title |
Towards a Robust Evaluation Framework for Generative Urban Design |
doi |
https://doi.org/10.52842/conf.ecaade.2024.1.529
|
source |
Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 529–538 |
summary |
This paper critically reviews the evaluation methods employed in the Generative Urban Design (GUD) literature. The review reveals various evaluation methods, including human-based, performance-based, and statistical evaluation. An analysis of the evaluation methods shows that each approach has limitations, and none fully addresses the unique challenges of evaluating GUD. The paper concludes that more robust and comprehensive evaluation methods are needed for GUD. The findings of this study have implications for GUD researchers, providing them with a critical understanding of the strengths and limitations of current evaluation methods and suggesting directions for future research. |
keywords |
Machine-Learning, Generative Urban Design, Deep Learning, GAN, FID score |
series |
eCAADe |
email |
|
full text |
file.pdf (419,026 bytes) |
references |
Content-type: text/plain
|
Allen-Dumas, M.R. et al. (2022)
Generative adversarial networks for ensemble projections of future urban morphology
, Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities. SIGSPATIAL '22: The 30th International Conference on Advances in Geographic Information Systems, Seattle Washington: ACM, pp. 1-6
|
|
|
|
Boim, A., Dortheimer, J. and Sprecher, A. (2022)
A Machine-Learning Approach to Urban Design Interventions In Non-Planned Settlements
, CAADRIA 2022: Post-Carbon, Sydney, Australia, pp. 223-232
|
|
|
|
Borji, A. (2019)
Pros and cons of gan evaluation measures
, Computer vision and image understanding, 179, pp. 41-65
|
|
|
|
Burry, M. (2022)
A new agenda for AI-based urban design and planning
, Artificial Intelligence in Urban Planning and Design. Elsevier, pp. 3-20
|
|
|
|
Carvalho, G.S. and Ponti, M.A. (2023)
Dendrogram distance: an evaluation metric for generative networks using hierarchical clustering
, arXiv preprint arXiv:2311.16894 [Preprint]
|
|
|
|
Cheng, S., Leung, C.K.S. and Van Ameijde, J. (2022)
Evaluating the Accessibility of Amenities toward Walkable Neighourhoods: an Integrated Method for Testing Alternatives in a Generative Urban Design Process
, CAADRIA 2022: Post-Carbon, Sydney, Australia, pp. 495-504
|
|
|
|
De Miguel Rodríguez, J. et al. (2020)
Generation of geometric interpolations of building types with deep variational autoencoders
, Design Science, 6, p. e34
|
|
|
|
Deshpande, R. (2023)
Generative Pre-Trained Transformers for 15-Minute City Design
, Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 595-604. CUMINCAD
|
|
|
|
Dong, Z. and Lin, J. (2023)
Nolli Map: Interpretation of Urban Morphology Based on Machine Learning
, P.F. Yuan et al. (eds) Hybrid Intelligence. Singapore: Springer Nature Singapore, pp. 274-283
|
|
|
|
Dong, Z. (2022)
Perceiving Fabric Immersed in Time, an Exploration of Urban Cognitive Capabilities of Neural Networks
, Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 263-272. CUMINCAD
|
|
|
|
Du, Z. et al. (2022)
3D building fabrication with geometry and texture coordination via hybrid GAN
, Journal of Ambient Intelligence and Humanized Computing, 13(11), pp. 5177-5188
|
|
|
|
Fattahi Tabasi, S. et al. (2023)
Optimizing urban layouts through computational generative design: density distribution and shape optimization
, Architectural Engineering and Design Management, pp. 1-21
|
|
|
|
Gan, W. et al. (2023)
UDGAN: A new urban design inspiration approach driven by using generative adversarial networks
, Journal of Computational Design and Engineering, 11(1), pp. 305-324
|
|
|
|
Garozzo, R. et al. (2021)
Knowledge-based generative adversarial networks for scene understanding in Cultural Heritage
, Journal of Archaeological Science: Reports, 35, p. 102736
|
|
|
|
Goodfellow, I. et al. (2014)
Generative adversarial nets
, Advances in neural information processing systems, 27
|
|
|
|
Han, Z., Yan, W. and Liu, G. (2021)
A Performance-Based Urban Block Generative Design Using Deep Reinforcement Learning and Computer Vision
, P.F. Yuan et al. (eds) Proceedings of the 2020 DigitalFUTURES. Singapore: Springer Singapore, pp. 134-143
|
|
|
|
He, J. et al. (2023)
Extracting human perceptions from street view images for better assessing urban renewal potential
, Cities, 134, p. 104189
|
|
|
|
Jiang, F., Ma, J., Webster, C.J., Chiaradia, A.J.F., et al. (2023)
Generative urban design: A systematic review on problem formulation, design generation, and decision-making
, Progress in Planning, p. 100795
|
|
|
|
Jiang, F., Ma, J., Webster, C.J., Li, X., et al. (2023)
Building layout generation using site-embedded GAN model
, Automation in Construction, 151, p. 104888
|
|
|
|
Jiralerspong, M. et al. (2023)
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
, arXiv
|
|
|
|
last changed |
2024/11/17 22:05 |
|