Clockwise from left to right: Matthias Nießner, Chris Bregler, ctrl shift face, Eakta Jain, and Sylvain Paris
For the latest episode of SIGGRAPH Spotlight, SIGGRAPH 2021 Technical Papers Chair Sylvain Paris (fellow, Adobe Research) is joined by a group of the computer graphics industry’s best and brightest to tackle the subject of deepfakes — from the history of deepfake tech through to how it’s being used today. Press play to hear insight in two parts from Chris Bregler (sr. staff scientist, Google AI), Eakta Jain (assistant professor, University of Florida), and Matthias Nießner (professor, TU München) [Part 1 – 0:00:34], and from ctrl shift face (independent artist) [Part 2 – 0:52:55].
Don’t miss a single episode of the SIGGRAPH Spotlight podcast! Subscribe to show in your favorite podcast app: Apple Podcasts (iTunes), Spotify, Stitcher, SoundCloud, iHeartRadio, Amazon Music, or Google Podcasts.
Resources From Today’s Episode
- Deepfake Detection Dataset from Google AI
- SIGGRAPH 2018 Technical Paper, “Deep Video Portraits”
- “Sassy Justice” video
- CISA graphic novel, “Real Fake”
- MIT’s “In the Event of Moon Disaster”
- Content Authenticity Initiative
- “Bill Hader impersonates Arnold Schwarzenegger [DeepFake]” video
About Our Guests
Dr. Matthias Nießner is a professor at the Technical University of Munich where he leads the Visual Computing Lab. Before, he was a visiting assistant professor at Stanford University. Nießner’s research lies at the intersection of computer vision, graphics, and machine learning, where he is particularly interested in cutting-edge techniques for 3D reconstruction, semantic 3D scene understanding, video editing, and AI-driven video synthesis. In total, he has published over 70 academic publications, including 22 papers in the prestigious ACM Transactions on Graphics (SIGGRAPH / SIGGRAPH Asia) journal and 26 works at leading vision conferences (CVPR, ECCV, ICCV); several of these works won best paper awards, including at SIGCHI’14, HPG’15, SPG’18, and the SIGGRAPH 2016 Emerging Technologies award for the best live demo. His work also enjoys wide media coverage, with features in The New York Times, The Wall Street Journal, Spiegel, MIT Technology Review, and many more, including a TV appearance on “Jimmy Kimmel Live” where he demonstrated the popular Face2Face technique.
Eakta Jain is an assistant professor of computer and information science and engineering at the University of Florida. She is interested in visual attention, graphics, and virtual reality. Currently, she is especially interested in the privacy and security implications of large-scale behavioral data collection, with a focus on eye tracking data. Eakta was trained at Carnegie Mellon University and IIT Kanpur. She has worked at Texas Instruments R&D labs, Disney Research Pittsburgh, and Walt Disney Animation Studios. Her research group is funded by the National Science Foundation, National Institutes of Mental Health, Florida Department of Transportation, and faculty awards from Facebook and Google.
Chris Bregler is a senior staff scientist and research lead at Google for media integrity efforts and other initiatives to combat disinformation including DeepFakes, CheapFakes, Fake News, and many other areas. He received an Academy Award in the Science and Technology category for his visual effects work, an IEEE Longuet-Higgins Prize for “Fundamental Contributions in Computer Vision that Have Withstood the Test of Time,” an Olympus Prize, and as professor at Stanford University and NYU he was named a Stanford Joyce Faculty Fellow, Terman Fellow, and Sloan Research Fellow. He also worked for Interval, Disney, and LucasFilm’s ILM. He received his M.S. and Ph.D. in computer science from University of California, Berkeley.
ctrl shift face is an independent artist and YouTube creator who makes entertaining videos using deepfake technology. Most recently, ctrl shift face is credited as a contributor to the “Sassy Justice” web series from “South Park” creators Trey Parker and Matt Stone.
Submissions to the SIGGRAPH 2021 Technical Papers program are now open. Submit your deepfakes or related research today!