A new GPU-based facial reenactment technique tracks the expression of a source actor and transfers it to a target actor in real-time – which translates into you being able to control another human’s expressions. The project is a collaboration of researchers from Stanford University, Max Planck Institute for Informatics and University of Erlangen-Nuremberg.
The novelty of the approach lies in the transfer and photorealistic re-rendering of facial deformations and detail into the target video in a way that the newly-synthesized expressions are virtually indistinguishable from a real video.
The video demo uses a setup consisting of a GeForce GTX 980 GPU and is something definitely worth watching – it’s a matter of time before Disney adopts this technology!
You can read more about the project in their paper titled “Real-time Expression Transfer for Facial Reenactment.“
AI-Generated Summary
- Researchers from Stanford University, Max Planck Institute for Informatics, and University of Erlangen-Nuremberg have collaborated on a new GPU-based facial reenactment technique that transfers a source actor's expression to a target actor in real-time.
- This technique involves the transfer and photorealistic re-rendering of facial deformations and detail into the target video, making the newly-synthesized expressions almost indistinguishable from real video.
- The project used a GeForce GTX 980 GPU for its video demo, which has potential applications in industries such as entertainment, possibly being adopted by companies like DISNEY.
AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
