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 acadia19_370
authors Mohammad, Ali; Beorkrem, Christopher; Ellinger, Jefferson
year 2019
title Hybrid Elevations using GAN Networks
source ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 370-379
summary This project is an attempt to develop and test a method for generating one-sided hybrid exterior building elevations using designerís base criteria and design rule sets as inputs in an advanced artificial intelligence network. Architects are using computational design to expedite the iteration process in an efficient manner. Optimization techniques utilizing genetic solvers allow designers to explore broad sets of iterations within a predefined subset. However, with the application of artificial intelligence networks these fields of exploration can be expanded upon to develop ranges of exploration which can explore iterations outside of typical ranges. This paper explores the use of Generative Adversarial Networks (GAN) to explore and demonstrate their possible capabilities to typical design problems. In this instance we are exploring their application in the development of architectural elevations.
series ACADIA
type normal paper
full text file.pdf (2,060,966 bytes)
references Content-type: text/plain
last changed 2019/12/18 08:03
pick and add to favorite papersHOMELOGIN (you are user _anon_216881 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002