Session: Making Faces
Thursday, 9 August
10:30 am - 12:15 pm
Room 4
Chair: Cindy Grimm, Whashington University in St. Louis
Animation Transfer using Face In Motion technology (models © 2005 Dygrafilms).
SIGGRAPH'07
We would like to thank everyone that attended our sketch session and all the people that have shown enormous interest in our technology. We also thank SIGGRAPH for providing a great environment to meet with friends and colleagues.
Feel free to download our sketch, video and presentation and hope to see you all next year.
Sketch
Title: Fast and reusable facial rigging and animation
Abstract. Reproducing the subtleties of a face through animation requires developing a sophisticated character rig. But, creating by hand the inner structure and controls of each character is a very labor-intensive and time-consuming task. We developed an application that is 90--99% faster than traditional manual rigging. The application automatically transfers the rig and animations from the source to a target model. Unlike prior work related to morphing and re-targeting that focus on transferring animations, we transfer the complete facial setup in addition to animations. Our method is general, so artists can define their own rig and then quickly apply it to different models, even with disparate proportions and appearance (human, cartoon or fantastic). This gives artists complete freedom to manipulate the characters: they can create new animations and not be limited by pre-generated ones.
Sketch:
PDF (221 KB)
Video
The video shows the results of several tests performed with Fimmie, Face In Motion's novel technology. It compares the output automatically generated by the system with the manual results created by the artists.
Video:
AVI (9,62 MB) 3 min
(codec x264, size 720x576, 24 fps)
Use VLC to play this video.
Presentation
The presentation describes the use of Face In Motion's technology from the user's point of view. It details the system pipeline and main features. Last, it shows the result of transferring the facial rig between models with different shape and appearance.
Presentation:
PDF (10.9 MB)