Encoded Images: Representational protocols for integrating cGANs in iterative computational design processes

Publications: Chapter in Book/Report/Conference proceedingBook chapterResearchpeer-review


In this paper, we explore Conditional Generative Adversarial Networks (cGANs) as a new way of bridging the gap between design and analysis in contemporary architectural practice. By replacing analytical FEA modelling with cGAN predictions, we develop novel workflows that support iterative computational design and digital fabrication processes in new ways. This paper reports two case studies of increasing complexity that utilize cGANs for structural analysis.
Central to both experiments is the representation of information within the dataset the cGAN is trained on. We contribute an experimental representational technique to encode multiple layers of geometric and performative description into false colour images, which we then use to train a Pix2Pix neural network architecture on entirely digital generated datasets as a proxy for the performance of physically fabricated elements. The paper
describes the representational workflow, reports the process and results of training and their integration into the design experiments. Lastly, we identify potentials and limits of this approach within the design processes.
Original languageEnglish
Title of host publicationACADIA 2020 Distributed Proximities : Proceedings of the 40th Annual Conference of the Association for Computer Aided Design in Architecture
Publication date12 Aug 2021
ISBN (Print)978-0578952130
Publication statusPublished - 12 Aug 2021


  • Deep Learning
  • Neural Networks
  • data representation
  • finite element analysis
  • Computational Design

Artistic research

  • No

Cite this