Lisa Graziani (University of Florence)
Feb 5, 2020 – 11:00 AM
DIISM, Artificial Intelligence laboratory (room 201), Siena SI
Sketch generation from photos can be seen as a classic task of image to image translation with GANs. But in our work the sketch generation is addressed as an unsupervised problem based on a vectorial representation of the lines present in the images. The generative mechanism is based on a sort of “creative loop” where four cooperating modules operate. The learning process is driven by some creative schemes through constraints.