Some experts say that a truly intelligent machine must be creative. My work in image-to-image translation tasks shows a lot of promise in machine creativity. It seems within reach to train a universal image-to-image network capable of translating any natural image to many natural images of other classes in creative and unseen ways.
Yazeed Alharbi is a Ph.D. candidate under the supervision of Prof. Peter Wonka at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST).
Education and Early Career
In 2015, Yazeed obtained his bachelor degree from Purdue University in the computer graphics and visualization track, with a minor in philosophy. In 2018, he received his master degree from King Abdullah University of Science and Technology (KAUST). He mainly learned about computer vision and the process of publication in that field.
Research Interest
Currently, Alharbi research is focused on using generative adversarial networks (GANs) to convert an image from one domain to another. Some examples are converting real images to paintings, or converting CGI to realistic images. More specifically, he is examining methods of generating many different outputs given one input (multimodality).
Honors and Awards
Yazeed Alharbi was part of the KAUST Gifted Student Program (KGSP) in the period from 2011 to 2017.
Selected Publications
[CVPR 2019] Latent Filter Scaling for Multimodal Unsupervised Image-to-image Translation. Yazeed Alharbi, Neil Smith, Peter Wonka.
Yazeed master thesis is “Marker Detection in Aerial Images”.
Education Profile
- M.S., Computer Science, KAUST, Thuwal, Saudi Arabia, 2018
- B.S., Computer Science, Purdue University, West Lafayette, IN, USA, 2015
Professional Memberships
KAUST Gifted Student Program (2010-2017)
