no code implementations • 12 Jul 2021 • Terence Broad, Sebastian Berns, Simon Colton, Mick Grierson
Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results.
no code implementations • 5 Jul 2021 • Sebastian Berns, Terence Broad, Christian Guckelsberger, Simon Colton
The framework provides opportunities to hand over creative responsibilities to a generative system as targets for automation.
1 code implementation • 25 May 2020 • Terence Broad, Frederic Fol Leymarie, Mick Grierson
This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant features of the generated images.
no code implementations • 17 Feb 2020 • Terence Broad, Frederic Fol Leymarie, Mick Grierson
Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that (to the untrained eye) are indistinguishable from real images.
no code implementations • 6 Oct 2019 • Terence Broad, Mick Grierson
This paper details a developing artistic practice around an ongoing series of works called (un)stable equilibrium.
no code implementations • 6 Oct 2019 • Terence Broad, Mick Grierson
In this work we present a method for fine-tuning pre-trained GANs with features from different datasets, resulting in the transformation of the output distribution into a new distribution with novel characteristics.