Methods and systems for animating facial features, and methods and systems for expression transformation

• US 20060192785A1
• Filed: 04/24/2006
• Published: 08/31/2006
• Est. Priority Date: 08/30/2000
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Kang, Sing Bing, Olynyk, Kirk, Guenter, Brian K., Raghupathy, Sashi, Marschner, Stephen
• Granted Patent: US 7,450,126 B2
• Time in Patent Office: Days
• US Class Current: 345/473
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 15/04 Texture mapping
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 17/205 Re-meshing
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: Y10S 345/956 Language driven animation

Abstract

The illustrated and described embodiments describe techniques for capturing data that describes 3-dimensional (3-D) aspects of a face, transforming facial motion from one individual to another in a realistic manner, and modeling skin reflectance.

Claims

1. A system for animating facial features comprising:

means for defining a subdivision surface that approximates geometry of a plurality of different faces; and

means for fitting the same subdivision surface to each of the plurality of faces.

2. The system of claim 1, wherein said means for defining comprises means for defining the subdivision surface with a coarse mesh structure.

3. The system of claim 2, wherein the coarse mesh structure comprises a triangular mesh.

4. The system of claim 1, wherein said means for fitting comprises means for performing a continuous optimization operation over vertex positions of the subdivision surface.

5. The system of claim 1, wherein said means for fitting comprises means for fitting the subdivision surface to the faces without altering the connectivity of a mesh that defines the subdivision surface.

6. The system of claim 1, wherein said means for fitting comprises means for minimizing a smoothing functional associated with a mesh that defines the subdivision surface.

7. The system of claim 1, wherein said means for fitting comprises means for selecting one or more constraints associated with a mesh that defines the subdivision surface and means for fitting those constraints directly to corresponding points on the faces.

8. The system of claim 7, wherein the constraints are associated with one of the eyes, nose or mouth.

9. The system of claim 1, wherein said means for fitting comprises means for minimizing a functional that includes terms for distance, smoothness, and constraints.

10. The system of claim 1, wherein said means for fitting comprises means for solving a sequence of linear least-squares problems.

11. A method of animating facial features comprising:

defining a subdivision surface that approximates geometry of a plurality of different faces;

fitting the same subdivision surface to each of the plurality of faces to establish a correspondence between the faces; and

using the correspondence between the faces to transform an expression of one face into an expression of another face.

12. A method of animating facial features comprising:

measuring 3-dimensional data for a plurality of different faces to provide corresponding face models;

defining only one generic face model that is to be used to map to each corresponding face model;

selecting a plurality of points on the generic face model that are to be mapped directly to corresponding points on each of the corresponding face models; and

fitting the generic face model to each of the corresponding face models, said fitting comprising mapping each of the selected points directly to the corresponding points on each of the corresponding face models.

13. The method of claim 12, wherein:

said defining comprises defining a subdivision surface from a base mesh structure, the subdivision surface containing a plurality of vertices and approximating the geometry of the face models; and

said fitting comprises manipulating only the positions of the vertices of the subdivision surface.

14. The method of claim 12, wherein said fitting comprises manipulating a base mesh that defines a subdivision surface.

15. The method of claim 12, wherein said fitting comprises manipulating a base mesh that defines a subdivision surface without altering the connectivity of the base mesh.

16. The method of claim 12, wherein said measuring comprises using a laser range scan to measure the 3-dimensional data.