In the overlap of computer vision and machine learning, Dr. Ilke Demir's research focuses on generative models for digitizing the real world, deep fake detection and generation techniques, analysis and synthesis approaches in geospatial machine learning, and computational geometry for synthesis and fabrication. Currently, she is a Senior Research Scientist at Intel, leading the research in the world's largest volumetric capture stage, revolutionizing the entertainment industry.
She earned her B.S. degree in Computer Engineering from Middle East Technical University with a minor in Electrical Engineering, and her M.S. and Ph.D. degrees in Computer Science from Purdue University, with her dissertation discussing geometric and topological shape processing approaches for reconstruction, modeling, and synthesis; which pioneered the area of proceduralization. Afterward, Dr. Demir joined Facebook as a Postdoctoral Research Scientist working with Ramesh Raskar, where their team developed the breakthrough innovation on generative street addresses. Her research further included deep learning approaches for human behavior understanding in virtual reality, geospatial machine learning for map creation, and 3D reconstruction at scale.In addition to her publications in top-tier venues (SIGGRAPH, ICCV, CVPR), she has organized workshops, competitions, and courses in deep learning, computer vision, and graphics (DeepGlobe, SkelNetOn, WiCV, SUMO, DLGC, OpenEDS, etc.).
Dr. Demir received numerous awards and honors such as ACM Distinguished Speaker, Jack Dangermond Award, Bilsland Dissertation Fellowship, IEEE Industry Distinguished Lecturer, and GHC Fellow, in addition to her best paper/poster/reviewer awards. Her work on geospatial machine learning and deep fakes received significant attention from researchers and media outlets around the world, such as The Independent, VentureBeat, MIT Tech Review, and Liberation, to name a few. Dr. Demir has also been actively involved in women in science organisms, always being an advocate for women and underrepresented minorities.
Sub-specialities:
Artificial Intelligence, Machine Learning, Computer Vision, 3D Vision, Computational Geometry, Generative Models, Deep Learning, Deep Fakes
[SHARE]
Expert DirectLink
-
STRANGE BLOOD FLOW IS THE SECRET TO DETECTING DEEPFAKES, NEW RESEARCH SUGGESTS
The Independent [October 2, 2020] -
The Subtle Effects of Blood Circulation Can Be Used to Detect Deep Fakes
IEEE Spectrum [September 28, 2020] -
AI researchers use heartbeat detection to identify deepfake videos
VentureBeat [September 3, 2020] -
From Observer to Leader: How Computer Vision Researcher Ilke Demir Found Her Voice
Wogrammer Interview [October 2, 2019] -
Analysis and Synthesis Approaches in Geospatial Machine Learning
IEEE GRSS TV [June 26, 2019] -
Peut-on créer des adresses sans manquer d’adresse ?
Liberation [December 2, 2018] -
Billions of people lack an address. Machine learning could change that.
MIT Tech Review [November 29, 2018] -
Women in Computer Vision: Ilke Demir
CVPR Daily by RSIP Vision [July 22, 2017]















