ABOUT THE SPEAKER
Paul Debevec - Computer graphics pioneer
Paul Debevec's digital inventions have powered the breathtaking visual effects in films like The Matrix, Superman Returns, King Kong and The Curious Case of Benjamin Button.

Why you should listen

Called "Hollywood's Master of Light" by MIT's Technology Review, Paul Debevec leads the Graphics Laboratory at USC's Institute for Creative Technologies, where he directs the development of the Light Stage systems, which capture and simulate how people and objects appear in real-world illumination.

His work on lighting digital objects has been used in films like X-Men, The Golden Compass and Terminator: Salvation. He leads the design of HDR Shop, the first high-dynamic-range image editing program. He has collaborated with TEDster Golan Levin on an interactive art installation called Rouen Revisited.

More profile about the speaker
Paul Debevec | Speaker | TED.com
TEDxUSC

Paul Debevec: Animating a photo-real digital face

Filmed:
881,584 views

Computer graphics trailblazer Paul Debevec explains the scene-stealing technology behind Digital Emily, a digitally constructed human face so realistic it stands up to multiple takes.
- Computer graphics pioneer
Paul Debevec's digital inventions have powered the breathtaking visual effects in films like The Matrix, Superman Returns, King Kong and The Curious Case of Benjamin Button. Full bio

Double-click the English transcript below to play the video.

00:18
One of the biggest challenges in computer graphics
0
0
3000
00:21
has been being able to create a photo-real,
1
3000
2000
00:23
digital human face.
2
5000
2000
00:25
And one of the reasons it is so difficult is that, unlike aliens and dinosaurs,
3
7000
3000
00:28
we look at human faces every day.
4
10000
3000
00:31
They are very important to how we communicate with each other.
5
13000
2000
00:33
As a result, we're tuned in to the subtlest things
6
15000
3000
00:36
that could possibly be wrong with a computer rendering,
7
18000
2000
00:38
in order to believe whether these things are realistic.
8
20000
3000
00:41
And what I'm going to do in the next five minutes
9
23000
2000
00:43
is take you through a process
10
25000
2000
00:45
where we tried to create a reasonably photo-realistic computer-generated face,
11
27000
3000
00:48
using some computer graphics technology we've developed,
12
30000
3000
00:51
and also some collaborators at a company called Image Metrics.
13
33000
2000
00:53
And we're going to try to do a photo-real face
14
35000
2000
00:55
of an actress named Emily O'Brien, who is right there.
15
37000
3000
00:58
And that's actually a completely computer-generated rendering of her face.
16
40000
3000
01:01
By the end of the talk, we're going to see it move.
17
43000
2000
01:03
The way that we did this is we tried to start with Emily herself,
18
45000
3000
01:06
who was gracious enough to come to our laboratory
19
48000
3000
01:09
in Marina Del Rey, and sit for a session in Light Stage 5.
20
51000
3000
01:12
This is a face-scanning sphere, with 156 white LEDs all around
21
54000
4000
01:16
that allow us to photograph her
22
58000
2000
01:18
in a series of very controlled illumination conditions.
23
60000
3000
01:21
And the lighting that we use these days looks something like this.
24
63000
3000
01:24
We shoot all of these photographs in about three seconds.
25
66000
2000
01:26
And we basically capture enough information
26
68000
3000
01:29
with video projector patterns that drape over the contours of her face,
27
71000
4000
01:33
and different principle directions of light from the light stage,
28
75000
2000
01:35
to figure out both the coarse-scale
29
77000
2000
01:37
and the fine-scale detail of her face.
30
79000
2000
01:39
If we zoom in on this photograph right here,
31
81000
2000
01:41
we can see it's a really nice photograph to have of her,
32
83000
2000
01:43
because she is lit from absolutely everywhere at the same time
33
85000
4000
01:47
to get a nice image of her facial texture.
34
89000
2000
01:49
And in addition, we've actually used polarizers on all the lights --
35
91000
3000
01:52
just like polarized sunglasses can block
36
94000
2000
01:54
the glare off of the road,
37
96000
2000
01:56
polarizers can block the shine off of the skin,
38
98000
2000
01:58
so we don't get all those specular reflections to take this map.
39
100000
3000
02:01
Now, if we turn the polarizers around just a little bit,
40
103000
2000
02:03
we can actually bring that specular reflection
41
105000
2000
02:05
of the skin back in,
42
107000
2000
02:07
and you can see she looks kind of shiny and oily at this point.
43
109000
3000
02:10
If you take the difference between these two images here,
44
112000
3000
02:13
you can get an image lit from the entire sphere of light
45
115000
2000
02:15
of just the shine off of Emily's skin.
46
117000
3000
02:18
I don't think any photograph like this had ever been taken
47
120000
2000
02:20
before we had done this.
48
122000
2000
02:22
And this is very important light to capture,
49
124000
3000
02:25
because this is the light that reflects off the first surface of the skin.
50
127000
2000
02:27
It doesn't get underneath the translucent
51
129000
2000
02:29
layers of the skin and blur out.
52
131000
2000
02:31
And, as a result, it's a very good cue
53
133000
2000
02:33
to the detailed shape of the skin-pore structure
54
135000
3000
02:36
and all of the fine wrinkles that all of us have,
55
138000
2000
02:38
the things that actually make us look like real humans.
56
140000
2000
02:40
So, if we use information that comes off of this specular reflection,
57
142000
4000
02:44
we can go from a traditional face scan
58
146000
2000
02:46
that might have the gross contours of the face and the basic shape,
59
148000
4000
02:50
and augment it with information
60
152000
2000
02:52
that puts in all of that skin pore structure and fine wrinkles.
61
154000
3000
02:55
And, even more importantly,
62
157000
2000
02:57
since this is a photometric process that only takes three seconds to capture,
63
159000
3000
03:00
we can shoot Emily
64
162000
2000
03:02
in just part of an afternoon,
65
164000
2000
03:04
in many different facial poses and facial expressions.
66
166000
3000
03:07
So, here you can see her moving her eyes around, moving her mouth around.
67
169000
3000
03:10
And these we're actually going to use to create a photo-real digital character.
68
172000
3000
03:13
If you take a look at these scans that we have of Emily,
69
175000
4000
03:17
you can see that the human face does an enormous amount of amazing things
70
179000
3000
03:20
as it goes into different facial expressions.
71
182000
3000
03:23
You can see things. Not only the face shape changes,
72
185000
3000
03:26
but all sorts of different skin buckling and skin wrinkling occurs.
73
188000
4000
03:30
You can see that the skin pore structure changes enormously
74
192000
4000
03:34
from stretched skin pores
75
196000
2000
03:36
to the regular skin texture.
76
198000
2000
03:38
You can see the furrows in the brow and how the microstructure changes there.
77
200000
3000
03:41
You can see muscles pulling down at flesh to bring her eyebrows down.
78
203000
4000
03:45
Her muscles bulging in her forehead when she winces like that.
79
207000
3000
03:48
In addition to this kind of high-resolution geometry,
80
210000
3000
03:51
since it's all captured with cameras, we've got a great texture map to use for the face.
81
213000
4000
03:55
And by looking at how the different color channels of the illumination,
82
217000
2000
03:57
the red and the green and the blue,
83
219000
2000
03:59
diffuse the light differently,
84
221000
2000
04:01
we can come up with a way of shading the skin on the computer.
85
223000
3000
04:04
Then, instead of looking like a plaster mannequin,
86
226000
3000
04:07
it actually looks like it's made out of living human flesh.
87
229000
3000
04:10
And this is what we used
88
232000
2000
04:12
to give to the company Image Metrics
89
234000
2000
04:14
to create a rigged, digital version of Emily.
90
236000
3000
04:17
We're just seeing the coarse-scale geometry here.
91
239000
2000
04:19
But they basically created a digital puppet of her,
92
241000
3000
04:22
where you can pull on these various strings,
93
244000
2000
04:24
and it actually moves her face in ways that are
94
246000
2000
04:26
completely consistent with the scans that we took.
95
248000
2000
04:28
And, in addition to the coarse-scale geometry,
96
250000
2000
04:30
they also used all of that detail
97
252000
2000
04:32
to create a set of what are called "displacement maps"
98
254000
3000
04:35
that animate as well.
99
257000
3000
04:38
These are the displacement maps here.
100
260000
2000
04:40
And you can see those different wrinkles actually show up as she animates.
101
262000
3000
04:43
So the next process was then to animate her.
102
265000
2000
04:45
We actually used one of her own performances to provide the source data.
103
267000
4000
04:49
So, by analyzing this video with computer vision techniques,
104
271000
3000
04:52
they were able to drive the facial rig
105
274000
2000
04:54
with the computer-generated performance.
106
276000
2000
04:56
So what you're going to see now, after this,
107
278000
2000
04:58
is a completely photo-real digital face.
108
280000
2000
05:00
We can turn the volume up a little bit if that's available.
109
282000
2000
05:02
Emily: Image Metrics is a markerless, performance-driven animation company.
110
284000
4000
05:06
We specialize in high-quality facial animation
111
288000
3000
05:09
for video games and films.
112
291000
2000
05:11
Image Metrics is a markerless, performance-driven animation company.
113
293000
4000
05:15
We specialize in high quality facial animation
114
297000
3000
05:18
for video games and films.
115
300000
3000
05:21
Paul Debevec: So, if we break that down into layers, here's that diffuse component
116
303000
2000
05:23
we saw in the first slide.
117
305000
2000
05:25
Here is the specular component animating.
118
307000
2000
05:27
You can see all the wrinkles happening there.
119
309000
2000
05:29
And there is the underlying wireframe mesh.
120
311000
5000
05:34
And that is Emily herself.
121
316000
2000
05:36
Now, where are we going with this here?
122
318000
2000
05:38
We've gone a little bit beyond Light Stage 5. This is Light Stage 6,
123
320000
4000
05:42
and we're looking at taking this technology
124
324000
2000
05:44
and applying it to whole human bodies.
125
326000
2000
05:46
This is Bruce Lawmen, one of our researchers in the group,
126
328000
2000
05:48
who graciously agreed to get captured running in the Light Stage.
127
330000
3000
05:51
And let's take a look at a computer-generated version
128
333000
2000
05:53
of Bruce, running in a new environment.
129
335000
2000
06:01
And thank you very much.
130
343000
2000
06:03
(Applause)
131
345000
1000

▲Back to top

ABOUT THE SPEAKER
Paul Debevec - Computer graphics pioneer
Paul Debevec's digital inventions have powered the breathtaking visual effects in films like The Matrix, Superman Returns, King Kong and The Curious Case of Benjamin Button.

Why you should listen

Called "Hollywood's Master of Light" by MIT's Technology Review, Paul Debevec leads the Graphics Laboratory at USC's Institute for Creative Technologies, where he directs the development of the Light Stage systems, which capture and simulate how people and objects appear in real-world illumination.

His work on lighting digital objects has been used in films like X-Men, The Golden Compass and Terminator: Salvation. He leads the design of HDR Shop, the first high-dynamic-range image editing program. He has collaborated with TEDster Golan Levin on an interactive art installation called Rouen Revisited.

More profile about the speaker
Paul Debevec | Speaker | TED.com