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
id ecaade2020_017
authors Chan, Yick Hin Edwin and Spaeth, A. Benjamin
year 2020
title Architectural Visualisation with Conditional Generative Adversarial Networks (cGAN). - What machines read in architectural sketches.
source Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 299-308
summary As a form of visual reasoning, sketching is a human cognitive activity instrumental to architectural design. In the process of sketching, abstract sketches invoke new mental imageries and subsequently lead to new sketches. This iterative transformation is repeated until the final design emerges. Artificial Intelligence and Deep Neural Networks have been developed to imitate human cognitive processes. Amongst these networks, the Conditional Generative Adversarial Network (cGAN) has been developed for image-to-image translation and is able to generate realistic images from abstract sketches. To mimic the cyclic process of abstracting and imaging in architectural concept design, a Cyclic-cGAN that consists of two cGANs is proposed in this paper. The first cGAN transforms sketches to images, while the second from images to sketches. The training of the Cyclic-cGAN is presented and its performance illustrated by using two sketches from well-known architects, and two from architecture students. The results show that the proposed Cyclic-cGAN can emulate architects' mode of visual reasoning through sketching. This novel approach of utilising deep neural networks may open the door for further development of Artificial Intelligence in assisting architects in conceptual design.
keywords visual cognition; design computation; machine learning; artificial intelligence
series eCAADe
full text file.pdf (7,159,152 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Chan, YHE (2020) Find in CUMINCAD Towards Artificial Discoveries with Cyclic-Conditional Generative Adversarial Network , Master's Thesis, University of Cardiff

100%; open Deng, L and Yu, D (2014) Find in CUMINCAD Deep learning: methods and applications , Foundations and Trends in Signal Processing, 7(3-4), pp. 197-387

100%; open Forbus, KD (2012) Find in CUMINCAD Vision and sketching , Perception, 41(9), pp. 1031-1039

100%; open Goldschmidt, G (1994) Find in CUMINCAD On visual design thinking: the vis kids of architecture , Design Studies, 15(2), pp. 158-174

100%; open Goodfellow, I, Pouget-Abadie, J, Mirza, M, Xu, B, Warde- Farley, D, Ozair, S, Courville, A and Bengio, Y (2014) Find in CUMINCAD Generative Adversarial Nets , Proceeding of International Conference on Neural Information Processing Systems (NIPS 2014),Neural Information Processing Systems Foundation, Inc., p. 2672-2680

100%; open Isola, P, Zhu, JY, Zhou, T and Efros, AA (2017) Find in CUMINCAD Image-To-Image Translation With Conditional Adversarial Networks , Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1125-1134

100%; open Kaufmann, G (1980) Find in CUMINCAD Imagery, language and cognition , Universitetsforl.

100%; open Mirza, M and Osindero, S (2014) Find in CUMINCAD Conditional generative adversarial nets , arXiv preprint arXiv:1411.1784,, pp. 1-7

100%; open Pallasmaa, J (2009) Find in CUMINCAD The thinking hand: Existential and embodied wisdom in architecture / Juhani Pallasmaa , Wiley and Chichester : John Wiley [distributor], Hoboken, N.J.

100%; open Schmidhuber, J (2015) Find in CUMINCAD Deep learning in neural networks: An overview , Neural networks, 61, pp. 85-117

100%; open Schon, DA and Wiggins, G (1992) Find in CUMINCAD Kinds of seeing and their functions in designing , Design Studies, 13(2), pp. 135-156

100%; open Simon, Herbert A. (1969) Find in CUMINCAD The Science of the Artificial , M.I.T. Press, Cambridge

100%; open Simon, Herbert A. (1983) Find in CUMINCAD WHY SHOULD MACHINES LEARN? , Michalski, RS, Carbonell, JG and Mitchell, TM (eds), Machine Learning, Morgan Kaufmann, pp. 25-37

100%; open Suwa, M and Tversky, B (1997) Find in CUMINCAD What do architects and students perceive in their design sketches? A protocol analysis , Design Studies, 18(4), pp. 385-403

100%; open Suwa, M, Gero, J and Purcell, T (1999) Find in CUMINCAD Unexpected Discoveries: How Designers Discover Hidden Features In Sketches , UNIVERSITY OF SYDNEY, SYDNEY, pp. 145-162

last changed 2020/09/09 09:54
pick and add to favorite papersHOMELOGIN (you are user _anon_665930 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002