Kyle Steinfeld

Intelligence Artificielle & Architecture Exhibit

Kyle Steinfeld

I displayed works at the Intelligence Artificielle & Architecture exhibit at the Pavillon De l'Arsenal in Paris. This exhibit "takes us through the main stages of an evolution that started from the studies on Modularity, Computer-aided Design (CAD), Parametrics and, finally, Artificial Intelligence", and was curated by Stanislas Chaillou.

Death Valley

NeurIPS 2017 Machine Learning for Creativity and Design

Kyle Steinfeld

In work exhibited at the NeurIPS 2017 Machine Learning for Creativity and Design, we developed a process for relating depthmaps extracted from Google Street View panoramas with the corresponding photographic information. A number of separate models were produced using limited geographic areas of selected cites. With these depthmap-to-panoramic cityscape models trained, we are able to generate new images from unrelated depthmaps which resembled photographic images of the selected cities. This is demonstrated using a javascript app (not currently online) and documented in still images and a series of videos.

Fresh Eyes - Toronto Exhibition

Kyle Steinfeld

In work exhibited at the University of Toronto in the context of the 2018 Smart Geometry Conference, three-dimensional architectural massings for single-family homes are generated by a generative adversarial network. This GAN is trained on a small dataset of three-dimensional models of homes falling into seventeen architectural styles, and that are represented as multi-view heightfield images.

Scripted By Purpose

Kyle Steinfeld

I displayed two original works at the Scripted by Purpose exhibit at the FUEL Gallery in Philadelphia. This exhibit of "explicit and encoded processes within design", curated by Marc Fornes (theverymany) and Skylar Tibbits (Sjet)

Not Far From Home

NeurIPS 2018 Machine Learning for Creativity and Design

Kyle Steinfeld

In work exhibited at the NeurIPS 2018 Machine Learning for Creativity and Design, three-dimensional architectural massings for single-family homes are generated by a generative adversarial network. This GAN is trained on a small dataset of three-dimensional models of homes falling into seventeen architectural styles, and that are represented as multi-view heightfield images. A process is developed for converting from 3d CAD model to 2d tiled heightfield image, and from the 2d heightfield images generated by GAN back to three-dimensions in voxel format.