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 ecaadesigradi2019_514
authors de Miguel, Jaime, Villafa?e, Maria Eugenia, Piškorec, Luka and Sancho-Caparrini, Fernando
year 2019
title Deep Form Finding - Using Variational Autoencoders for deep form finding of structural typologies
source Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 71-80
summary In this paper, we are aiming to present a methodology for generation, manipulation and form finding of structural typologies using variational autoencoders, a machine learning model based on neural networks. We are giving a detailed description of the neural network architecture used as well as the data representation based on the concept of a 3D-canvas with voxelized wireframes. In this 3D-canvas, the input geometry of the building typologies is represented through their connectivity map and subsequently augmented to increase the size of the training set. Our variational autoencoder model then learns a continuous latent distribution of the input data from which we can sample to generate new geometry instances, essentially hybrids of the initial input geometries. Finally, we present the results of these computational experiments and lay out the conclusions as well as outlook for future research in this field.
keywords artificial intelligence; deep neural networks; variational autoencoders; generative design; form finding; structural design
series eCAADeSIGraDi
full text file.pdf (17,399,674 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Cudzik, J and Radziszewski, K (2018) Find in CUMINCAD Artificial Intelligence Aided Architectural Design , Proceedings of the 36th eCAADe Conference - Volume 1

100%; open Doersch, C (2016) Find in CUMINCAD Tutorial on Variational Autoencoders , arXiv preprint, arXiv:1606.05908

100%; open Goodfellow, I, Bengio, Y and Courville, A (2016) Find in CUMINCAD Deep Learning , MIT Press

100%; open Gregor, K, Danihelka, I, Graves, A, Rezende, D and Wierstra, D (2015) Find in CUMINCAD Draw: A recurrent neural network for image generation , ICCV 2015

100%; open Ha, D and Eck, D (2017) Find in CUMINCAD A neural representation of sketch drawings , arXiv preprint, arXiv:1704.03477

100%; open Kelly, T, Guerrero, P, Steed, A, Wonka, P and Mitra, NJ (2018) Find in CUMINCAD FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs , arXiv preprint, arXiv:1806.07179

100%; open Kingma, DP and Welling, M (2014) Find in CUMINCAD Auto-encoding variational Bayes , ICLR 2014

100%; open Krizhevsky, A, Sutskever, I and Hinton, G (2012) Find in CUMINCAD Imagenet classification with deep convolutional neural networks , NIPS 2012

100%; open Luo, D, Wang, J and Xu, W (2018) Find in CUMINCAD Applied Automatic Machine Learning Process for Material Computation , Proceedings of the 36th eCAADe Conference - Volume 1

100%; open Radford, A, Metz, L and Chintala, S (2016) Find in CUMINCAD Unsupervised representation learning with deep convolutional generative adversarial networks , arXiv preprint, arXiv:1511.06434

100%; open Sohn, K, Lee, H and Yan, X (2015) Find in CUMINCAD Learning structured output representation using deep conditional generative models , NIPS 2015

100%; open Wang, TY, Cylan, D, Popovic, J and Mitra, NJ (2018) Find in CUMINCAD Learning a shared shape space for multimodal garment design , arXiv preprint, arXiv:1806.11335

100%; open White, T (2016) Find in CUMINCAD Sampling generative networks , arXiv preprint, arXiv:1609.04468

100%; open Wu, J, Zhang, C, Xue, T, Freeman, WT and Tenenbaum, JB (2016) Find in CUMINCAD Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , arXiv preprint, arXiv:1610.07584

100%; open Wu, K and Kilian, A (2018) Find in CUMINCAD Designing Natural Wood Log Structures with Stochastic Assembly and Deep Learning , Robotic Fabrication in Architecture, Art and Design 2018

100%; open Yetiş, G, Yetkin, O, Moon, K and K?l?ç, Ö (2018) Find in CUMINCAD A Novel Approach for Classification of Structural Elements in a 3D Model by Supervised Learning , Proceedings of the 36th eCAADe Conference - Volume 1

last changed 2019/08/26 20:24
pick and add to favorite papersHOMELOGIN (you are user _anon_36602 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002