Authors
Tianye Li, Timo Bolkart, Michael J Black, Hao Li, Javier Romero
University of Southern California; Max Planck Institute for Intelligent Systems; Body Labs Inc.; USC Institute for Creative Technologies
Portals
Summary
FLAME is a lightweight and expressive generic head model learned from over 33,000 of accurately aligned 3D scans. FLAME combines a linear identity shape space (trained from head scans of 3800 subjects) with an articulated neck, jaw, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes. FLAME model variations for shape, expression, pose, and appearance. For shape, expression, and appearance variations, the first three principal components are visualized at ±3 standard deviations. The pose variations are visualized at ±?/6 (head pose) and 0,?/8 (jaw articulation).
Abstract
The field of 3D face modeling has a large gap between high-end and low-end methods. At the high end, the best facial animation is indistinguishablefrom real humans, but this comes at the cost of extensive manual labor. At the low end, face capture from consumer depth sensors relies on 3D face models that are not expressive enough to capture the variability in natural facial shape and expression. We seek a middle ground by learning a facial model from thousands of accurately aligned 3D scans. Our FLAME model (Faces Learned with an Articulated Model and Expressions) is designed to work with existing graphics software and be easy to fit to data. FLAME uses a linear shape space trained from 3800 scans of human heads. FLAME combines this linear shape space with an articulated jaw, neck, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes. The pose and expression dependent articulations are learned from 4D face sequences in the D3DFACS dataset along with additional 4D sequences. We accurately register a template mesh to the scan sequences and make the D3DFACS registrations available for research purposes. In total the model is trained from over 33, 000 scans. FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model. We compare FLAME to these models by fitting them to static 3D scans and 4D sequences using the same optimization method. FLAME is significantly more accurate and is available for research purposes.
Contribution
- Our key contribution is a statistical head model that is significantly more accurate and expressive than existing head and facemodels, while remaining compatible with standard graphics software
- In contrast to existing models, FLAME explicitly modelshead pose and eyeball rotation
Related Works
Generic face models