making face

14
Making Face Presentation for computer graphics and vision XUYAN YAN

Upload: evysoso

Post on 19-Jan-2015

279 views

Category:

Technology


2 download

DESCRIPTION

my presentation for G&V

TRANSCRIPT

Page 1: Making Face

Making Face

Presentation for computer graphics and vision

XUYAN YAN

Page 2: Making Face

Motivation• It is a super hot topic nowdays, in computer gr

aphics industry ,that producing realistic, expressive animated faces. This technology has been used in creating believable virtual characters for moives and television.(e.g The Curious Case of Benjamin Button )

• I am quite interested in the topic of “making face” . As it seems so COOL and FUN!!

Page 3: Making Face

Making FacesGuenter, Grimm, Wood, Malvar, Pighin 1997

• Aim: Take video of an person, and generate a representation that allows reconstruction from any view

• Steps:– Take video with 6 cameras of a person speaking with 182 colore

d dots glued all over their face

Page 4: Making Face

– Track correspondences between dots(camera to camera & frame to frame) to determine dot motion over time

– Generate a 3D model by scanning the head (with the dots)

– For each frame, compute model vertex motion according to the (known) locations of the dots

– Two stage fit: first determine motion for a grid of points, then determine vertex motion

– To render, simply texture map the 3D fitted model• Textures come from the video streams• Remove dots from the textures, and the resulting holes filled in• Blend textures into one view independent texture

Page 5: Making Face

A Morphable ModelFor The Synthesis Of 3D Faces

Blanz, Vetter 1999

The technique derives a morphable face model by transforming the shape and texture of the examples into a vector space representation. New faces and expressions can be modeled by forming linear combinations of the prototypes.

Page 6: Making Face

• directly use the densely sampled geometry of the exemplar faces obtained by laser scanning of over 200 hundred person’s head.

• It built a morphable face model by automatically establishing correspondence between all of our 200 exemplar faces.

• The goal of such an extended morphable face model is to represent any face as a linear combination of a limited basis set of face prototypes.

• The interactive face modeling system enables human users to create new characters and to modify facial attributes by varying the model coefficients.

Page 7: Making Face

Synthesis of Faces

Modeler

ResultResult

Database

FaceAnalyzer

3D Head3D Head

Morphable

Face Model

Page 8: Making Face

Matching a Morphable 3D-Face-Model

• This model represent the geometry of a face with a shape-vector S and represent the texture of a face by a texture-vector T

R = Rendering Function p = Parameters for Pose, Illumination, ... Find optimal a, b, r !

4 4

2 2 3 3 4 4

3 3 2 2 1 1

1 1 R

R

Page 9: Making Face

Automated Parameter Estimation

Ambient: intensity, color Parallel: intensity, color,

directionColor: contrast, gains, offsets

150 shape coefficients 150 shape coefficients ii

150 texture coefficients 150 texture coefficients ii

– 3D Geometry head positionHead orientationfocal length

Face Parameters

– Light and Color

Page 10: Making Face

Example:

Page 11: Making Face

Examples

Page 12: Making Face

An interesting topic and What I will be working on in future: - exchange face in images...

It is also based on the the Morphable Model, which captures the range of possible shapes. and textures observed in a dataset of 3D scans.

This system applys an algorithm that estimates a textured 3D face model from a single image, along with all relevant scene parameters, such as 3D orientation, position, focal length of the camera, and the direction and intensity of illumination .

Given a set of about 7 feature points that are manually defined by the user in an interactive interface, the algorithm automatically fits a Morphable Model of 3D faces to the image and optimizes all model parameters.

Page 13: Making Face

Exchange

Page 14: Making Face

Reference

• Brian Guenter, Cindy Grimm, Henrique Malvar, Daniel Wood, Making Faces, SIGGRAPH 1998.

• V. Blanz, C. Basso, T. Poggio and T. Vetter, Reanimating Faces in Images and Video, EUROGRAPHICS 2003.

• V. Blanz, K. Scherbaum, T. Vetter, H.P. Seidel, Exchanging Faces in Images, EUROGRAPHICS 2004.