JUNE 8 & 9, 2020 TRACKS
Real-Time @ SIGGRAPH – Papers
Painting with a Deep Generative Model
David Bau – Massachusetts Institute of Technology
We explore how the neurons inside Generative Adversarial Networks (GANs) – deep networks that are trained to synthesize realistic images – reveal a fascinating decomposition of the visual world. We show to find these neurons, and we demonstrate how to control them to use a GAN like a semantic paintbrush.
Ph.D. Candidate in Electrical Engineering and Computer Science – Massachusetts Institute of Technology