Microsoft Develops Accurate Technique for 3D Facial Modeling
By Rob Scott
August 9, 2011
August 9, 2011
- Researchers from Microsoft’s Beijing lab have developed a technique to automatically model human faces in 3D with a new level of accuracy.
- According to the research, the new approach can acquire “high-fidelity 3D facial performances with realistic dynamic wrinkles and finescale facial details.”
- The technique combines 3D scanning technology with a motion-capture system, in addition to what Geekwire describes as “a technique they developed to determine the minimal number of face scans needed to create an accurate model, which makes the system faster and more efficient.”
- The research paper will be presented this week at the SIGGRAPH Conference in Vancouver.
- ETCentric staffer Phil Lelyveld comments: “This more-accurate facial modeling, tied to game engine character behavior generation, will make for some very interesting experiences. There was a recent story on an emotional (versus Q&A response) Turing test. Would you hurt a visually realistic avatar?”
No Comments Yet
You can be the first to comment!
Leave a comment
You must be logged in to post a comment.