Kyle Steinfeld, Titus Ebbecke, Georgios Grigoriadis, & David Zhou
A dataset of fragmented and decontextualized Greco-Roman sculptural relief underlies the generation of uncanny forms that straddle the unrecognizable and the familiar. Samples include those drawn from the Pergamon Altar: a Greek construction originating in modern-day Turkey, disassembled in the late 19th century, and re-assembled in the early 20th century in a Berlin museum. The project operates similarly. It begins with a disassembly of selected sculptural forms into fragments that can be described as deformations of a flat sheet. Where ML processes often struggle to describe three-dimensional form, these "vector displacement maps" are comprehensible to the machine, and serve to train a neural network - a gently modified implementation of StyleGAN - to understand the form-language of the selected source material. Recalling the rhythmic symmetry of frieze patterns found in traditional Western ornament, a "walk" through the latent space of Greco-Roman sculptural forms is aggregated across a surface in high relief.
A pipeline is developed for representing 3d polygon meshes as 2d vector displacement maps, and is illustrated in artificialis_releivo_supplement.jpg (not intended for exhibition). Given a sample form (1), a fragment (2) is selected and "squashed" onto a plane, with displacements between points on the plane and locations on the 3d mesh stored as vectors separated into their x,y, and z components (3). This vector information is stored as the RGB channels of a raster image (4), a format that is both amenable to a GAN, and is able to be re-interpreted as vector displacements (5) to reproduce similar three-dimensional sculptural forms (6). These synthetic sculptural forms may be combined and aggregated in various ways that are suitable for fabrication via 3d printing or CNC milling. At the time of writing, several cast bronze pieces are in production for display at the Italian Pavilion of the Venice Architecture Biennale in mid-November. Images of these pieces can be made available for exhibition at NeurIPS.
More to come!