Title: A High Resolution Geometry Capture System for Facial Performance
1(No Transcript)
2A High Resolution Geometry Capture System for
Facial Performance
- Wan-Chun Ma
- Andrew Jones
- Tim Hawkins
- Jen-Yuan Chiang
- Paul Debevec
- USC Institute for Creative Technologies
3(No Transcript)
4(No Transcript)
5(No Transcript)
6Gradient illumination
Real-time acquisition
Motion capture
7Other Acquisition Systems
Gradient Illumination
Wrinkle measurement
Structured light
Ma et al. 2007
Li Zhang et al. 2004
Bickel et al. 2007
Song Zhang et al. 2006
8LCD Projector
Canon 1ds Mark III Stereo Cameras
9Light Stage 5 162 White LEDS
10Spherical Gradient Normals
X
y
z
Ma et al. Rapid Acquisition of Diffuse and
Specular Normal Maps from Polarized Spherical
Gradient Illumination, EGSR 2007
11Structured light scan Diffuse normals
12Spherical Gradient Normals
X
y
z
Ma et al. Rapid Acquisition of Diffuse and
Specular Normal Maps from Polarized Spherical
Gradient Illumination, EGSR 2007
13Structured light scan Diffuse normals
14Structured light scan Specular normals
15Light Stage 5
LCD projector
V10
Canon 1ds Mark III
16Light Stage 5
MULE high-speed projector
V10
Vision Research Phantom V10 cameras
17(No Transcript)
18High-speed video
19Gradient illumination
Projector patterns
Repeat patterns 24-30 times per second
20Mechanical polarizer flipper
21Ferro-electric shutter
Diffuse
Specular
22Polarized beam splitter
Ferroelectric shutter
Diffuse
Specular
23Color space seperation
Ferroelectric shutter
Diffuse
Specular
Beam splitter
24(No Transcript)
25Rendering using color-space normal maps
26(No Transcript)
27(No Transcript)
28Face replacement
29Face replacement
30?
31Tension Maps / Wrinkle maps
Christopher Oat, SIGGRAPH 2007 Courses Blend
between artistically drawn bump maps
32Can we learn where wrinkles form?
33Capture geometry motion capture
34(No Transcript)
35Register texture space
Texture space
Image space
36Register texture space
Texture space
Image space
37Wrinkle Changes vs. Deformation
38Wrinkle Changes vs. Deformation
Angry
39Wrinkle Changes vs. Deformation
Surprise
40Polynomial Displacement Maps
(u,v)
2D strain space
Du,v(du,dv) a0du2 a1dv2 a2dudv a3du
a4dv a5
Displacement maps
41Polynomial Texture Maps
(u,v)
2D lighting space
Lu,v(lu,lv) a0lu2 a1lv2 a2lulv a3lu
a4lv a5
Displacement maps
Malzbender et al. 2001
42(No Transcript)
43Neutral expression
Neutral expression without detail
44Thin shell deformation using mocap points Botsch
2004
45Add medium resolution 3D displacement
46Result
Ground truth
Add high resolution 1D displacement
47Result
Ground truth
48(No Transcript)
49(No Transcript)
50(No Transcript)
51(No Transcript)
52(No Transcript)
53(No Transcript)
54Conclusions
Dynamic detail detail is important
High-resolution synthesis
High-resolution capture
55Future Work
- Ear-to-ear geometry
- Eyes, mouth, hair
- Improved reflectance properties
- Optimal training dataset
56SIGGRAPH 2008collaboration with
Tech Talk Getting Real with Emily Hall G, Room
2 August 13th, 1-230pm
57- Website http//gl.ict.usc.edu
Wan-Chun Ma, A Framework for Capture and
Synthesis of High Resolution Facial Geometry and
Performance, PhD Thesis, National Taiwan
University, July 2008 Thanks Jay Busch,
Abhijeet Ghosh, Magnus Lang, Matthias
Hullin, Michael Weigand, Monica Nichelson, Tom
Pereira
58(No Transcript)