Figure 1: In this example, a neural network is trained to dream or ‘hallucinate’ the features of arches on a given depth rendering to impose novel geometric structure into the input, and then to perform a style transfer between a rendered texture image from a student’s 3D model upon the result of the dreaming process. Works by Hannah Daugherty, Mariana Moreira de Carvalho, Imman Suleiman.
The painting Portrait of Edmond Belamy, by the Paris based art collective Obvious14 is based on a Generative Adversarial Network(GAN) that was trained with a set of 15,000 portrait examples spanning from the 14th to 19th century.
The complexity of the term Style consists in the unusual…
Results of 2D to 2D Style transfers based on Nolli plans and an image of the Moon: aspects of Estrangement and Defamiliarization prodoundly speak in those results about a design ecology in a Posthuman era.
A collection of two datasets – Baroque and Modern images – form the basis for the resulting models. (Image: Mariana Sanche & Leetee Wang, PennDesign, University of Pennsylvania 2018)
Results of 2D to 2D Style transfers based on plans: aspects of Estrangement and Defamiliarization profoundly speak in those results about a design ecology in a Posthuman era.
