Hallucinatory Archaeological Landscapes

Generative adversarial networks can ‘paint’ images or retrieve ‘photographs’ of things that never existed. We are training a GAN on a series of site photographs as part of a 3d photogrammetry workflow, to computationally hallucinate the site.

Below are some examples of other GAN projects

GAN Gogh

A project by Kenny Jones and Derrick Bonafilia, training a GAN on European Masters. Their code repo is on Github. Write-up on Towards Data Science.

Bone Trade

Graham and Huffer’s Bonetrade project has experimented with using GAN to suss out the visual rhetorics of social media posts with regard to the buying and selling of human remains.

Image Inpainting with Deep Learning

‘Inpainting refers to the art of restoring lost parts of an image and reconstructing them based on the background information. It refers to the process of filling in missing data in a designated region of visual input. In the digital world, it refers to the application of sophisticated algorithms to replace lost or corrupted parts of image data.’ Tarun Bonu