CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References
id ijac202321205
authors Zhuang, Xinwei; Ju, Yi; Yang, Allen; Caldas, Luisa
year 2023
title Synthesis and generation for 3D architecture volume with generative modeling
source International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 297–314
summary Generative design in architecture has long been studied, yet most algorithms are parameter-based and require explicit rules, and the design solutions are heavily experience-based. In the absence of a real understanding of the generation process of designing architecture and consensus evaluation matrices, empirical knowledge may be difficult to apply to similar projects or deliver to the next generation. We propose a workflow in the early design phase to synthesize and generate building morphology with artificial neural networks. Using 3D building models from the financial district of New York City as a case study, this research shows that neural networks can capture the implicit features and styles of the input dataset and create a population of design solutions that are coherent with the styles. We constructed our database using two different data representation formats, voxel matrix and signed distance function, to investigate the effect of shape representations on the performance of the generation of building shapes. A generative adversarial neural network and an auto decoder were used to generate the volume. Our study establishes the use of implicit learning to inform the design solution. Results show that both networks can grasp the implicit building forms and generate them with a similar style to the input data, between which the auto decoder with signed distance function representation provides the highest resolution results.
keywords data-driven design, 3D deep learning, architecture morphology representation, auto decoder, generative adversarial neural network
series journal
references Content-type: text/plain
Details Citation Select
100%; open Akmal Butt M and Maragos P (1998) Find in CUMINCAD Optimum design of chamfer distance transforms , IEEE Transactions on Image Processing

100%; open Belem C, Santos L and Leitao A (2019) Find in CUMINCAD On the impact of machine learning: architecture without architects , 18th International Conference, CAAD Futures 2019, Proceedings, Daejeon, Korea 2019:247-293.

100%; open Bernstein P (2022) Find in CUMINCAD Machine learning: Architecture in the age of artificial intelligence , London: RIBA Publishing, 2022, p. 200.

100%; open Bojanowski P, Joulin A, Lopez-Paz D, et al (2019) Find in CUMINCAD Optimizing the latent space of generative networks , Technical Report arXiv:1707.05776, arXiv

100%; open Chaillou S (2021) Find in CUMINCAD AI and architecture: An experimental perspective , The Routledge Companion to Artificial Intelligence in Architecture

100%; open Chang AX, Funkhouser T, Guibas L, et al (2015) Find in CUMINCAD ShapeNet: An information-Rich 3D model Repository , Technical Report arXiv:1512.03012, arXiv

100%; open Del Campo M and Leach N (2022) Find in CUMINCAD Can machines Hallucinate architecture? AI as design method , Architectural Design. 2022;92(3):6-13.

100%; open Delanoy J, Coeurjolly D, Lachaud JO, et al (2019) Find in CUMINCAD Combining voxel and normal predictions for multi- view 3D sketching , Computers and Graphics 2019;82:65-72. DOI:10.1016/j.cag.2019.05.024

100%; open Dhariwal P and Nichol A (2021) Find in CUMINCAD Diffusion models beat GANs on image synthesis , Advances in Neural Information Processing Systems. Curran Associates, Inc;34:8780-8794

100%; open Fletcher RR, Nakeshimana A and Olubeko O (2021) Find in CUMINCAD Addressing fairness, bias, and appropriate use of artificial intelligence and machine learning in global health , Frontiers in Artificial Intelligence 2021; 3(Article 561802).

100%; open Goodfellow IJ, Pouget-Abadie J, Mirza M, et al (2014) Find in CUMINCAD Generative adversarial networks , Technical Report arXiv: 1406.2661, arXiv

100%; open Huang W and Zheng H (2018) Find in CUMINCAD Architectural drawings recognition and generation through machine learning , Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA)

100%; open Isola P, Zhu JY, Zhou T, et al (2018) Find in CUMINCAD Image-to-Image translation with conditional adversarial networks , Technical Report arXiv:1611.07004, arXiv, 2018.

100%; open Jiang CM and Marcus P (2017) Find in CUMINCAD Hierarchical detail enhancing mesh-based shape generation with 3D generative adversarial network , arXiv:1709.07581.

100%; open Johnson J, Alahi A and Fei-Fei L (2016) Find in CUMINCAD Perceptual losses for real-time style transfer and super- resolution , Technical Report arXiv:1603.08155, arXiv

100%; open Kingma DP and Welling M (2013) Find in CUMINCAD Auto-encoding variational bayes , arXiv preprint arXiv:13126114

100%; open Kleineberg M, Fey M and Weichert F (2020) Find in CUMINCAD Adversarial generation of continuous implicit shape representations , arXiv: 200200349 [cs]

100%; open Leach N (2022) Find in CUMINCAD In the mirror of AI: What is creativity? , Architectural Intelligence 2022; 1(1 15).

100%; open Leotta MJ, Long C, Jacquet B, et al (2019) Find in CUMINCAD Urban semantic 3D reconstruction from multiview satellite imagery , In 2019 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW). Long Beach, CA, USA (IEEE): 1451-1460

100%; open Liu Y, Luo Y, Deng Q, et al (2020) Find in CUMINCAD Exploration of campus layout based on generative adversarial network , PF Yuan, J Yao, et al. (eds.) Proceedings of the 2020 DigitalFUTURES. Singapore: Springer. 2020:169-178. DOI: 10.1007/978-981-33-4400_616. Zhuang et al. 313

last changed 2024/04/17 14:30
pick and add to favorite papersHOMELOGIN (you are user _anon_691216 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002