Paul Debevec animates a photo-real digital face

86,268 views ・ 2009-10-20

TED


μ•„λž˜ μ˜λ¬Έμžλ§‰μ„ λ”λΈ”ν΄λ¦­ν•˜μ‹œλ©΄ μ˜μƒμ΄ μž¬μƒλ©λ‹ˆλ‹€.

λ²ˆμ—­: Taegon Kim κ²€ν† : Miryoung Lee
00:18
One of the biggest challenges in computer graphics
0
18330
3000
컴퓨터 κ·Έλž˜ν”½ λΆ„μ•Όμ˜ κ°€μž₯ 큰 과제 쀑 ν•˜λ‚˜λŠ”
00:21
has been being able to create a photo-real,
1
21330
2000
μ‚¬λžŒμ˜ 얼꡴을 λ””μ§€ν„Έλ‘œ ν¬ν† λ¦¬μ–Όν•˜κ²Œ
00:23
digital human face.
2
23330
2000
ν‘œν˜„ν•˜λŠ” κ²ƒμ΄μ—ˆμŠ΅λ‹ˆλ‹€.
00:25
And one of the reasons it is so difficult is that, unlike aliens and dinosaurs,
3
25330
3000
이 κ³Όμ œκ°€ μ–΄λ €μš΄ 이유 쀑 ν•˜λ‚˜λŠ” μš°λ¦¬κ°€ μ‚¬λžŒμ˜ 얼꡴을
00:28
we look at human faces every day.
4
28330
3000
μ™Έκ³„μΈμ΄λ‚˜ κ³΅λ£‘κ³ΌλŠ” 달리 맀일 보기 λ•Œλ¬Έμž…λ‹ˆλ‹€.
00:31
They are very important to how we communicate with each other.
5
31330
2000
얼꡴은 μ˜μ‚¬μ†Œν†΅μ„ ν•˜λŠ” 데 무척 μ€‘μš”ν•œ 역할을 ν•©λ‹ˆλ‹€.
00:33
As a result, we're tuned in to the subtlest things
6
33330
3000
κ·Έλž˜μ„œ μ»΄ν“¨ν„°λ‘œ λ§Œλ“  얼꡴을 μ§„μ§œμ²˜λŸΌ
00:36
that could possibly be wrong with a computer rendering,
7
36330
2000
λŠλ‚„ 수 있게 λ§Œλ“€κΈ° μœ„ν•΄ 컴퓨터 λ Œλ”λ§ κ³Όμ •μ—μ„œ
00:38
in order to believe whether these things are realistic.
8
38330
3000
잘λͺ»λ  수 μžˆλŠ” κ²ƒκΉŒμ§€ μ„Έμ„Έν•˜κ²Œ μ‘°μ •ν–ˆμŠ΅λ‹ˆλ‹€.
00:41
And what I'm going to do in the next five minutes
9
41330
2000
μ•žμœΌλ‘œ 5λΆ„κ°„ μ €λŠ” μ—¬λŸ¬λΆ„μ—κ²Œ μš°λ¦¬κ°€
00:43
is take you through a process
10
43330
2000
μ»΄ν“¨ν„°λ‘œ 포토리얼에 κ°€κΉŒμš΄ 얼꡴을 λ§Œλ“€κΈ° μœ„ν•΄
00:45
where we tried to create a reasonably photo-realistic computer-generated face,
11
45330
3000
λ…Έλ ₯ν•΄ 온 과정을 μ†Œκ°œν• κΉŒ ν•©λ‹ˆλ‹€.
00:48
using some computer graphics technology we've developed,
12
48330
3000
이 κ³Όμ •μ—μ„œ 저희가 이미지 λ©”νŠΈλ¦­μŠ€(Image Metrics)사와 곡동 κ°œλ°œν•œ
00:51
and also some collaborators at a company called Image Metrics.
13
51330
2000
컴퓨터 κ·Έλž˜ν”½ κΈ°μˆ μ„ μ‚¬μš©ν–ˆμŠ΅λ‹ˆλ‹€.
00:53
And we're going to try to do a photo-real face
14
53330
2000
μš°λ¦¬λŠ” μ—λ°€λ¦¬λΌλŠ” μ—¬λ°°μš°μ˜ 얼꡴을 ν¬ν† λ¦¬μ–Όν•˜κ²Œ
00:55
of an actress named Emily O'Brien, who is right there.
15
55330
3000
ν‘œν˜„ν•˜κ³ μž ν–ˆμŠ΅λ‹ˆλ‹€. μ§€κΈˆ 보고 κ³„μ‹œλŠ” 뢄이죠.
00:58
And that's actually a completely computer-generated rendering of her face.
16
58330
3000
그리고 이것이 μ»΄ν“¨ν„°λ§ŒμœΌλ‘œ λ Œλ”λ§ν•œ μ–Όκ΅΄μž…λ‹ˆλ‹€.
01:01
By the end of the talk, we're going to see it move.
17
61330
2000
강연이 끝날 μ―€μ—λŠ” 얼꡴이 μ›€μ§μ΄λŠ” 것을 λ³Ό 수 μžˆμŠ΅λ‹ˆλ‹€.
01:03
The way that we did this is we tried to start with Emily herself,
18
63330
3000
이 ν”„λ‘œμ νŠΈλŠ” μ²˜μŒλΆ€ν„° 에밀리와 ν•¨κ»˜ ν–ˆλŠ”λ°
01:06
who was gracious enough to come to our laboratory
19
66330
3000
μ—λ°€λ¦¬λŠ” κ³ λ§™κ²Œλ„ λ§ˆλ¦¬λ‚˜ 델 λ ˆμ΄μ— μžˆλŠ” 저희 μ—°κ΅¬μ†Œμ—
01:09
in Marina Del Rey, and sit for a session in Light Stage 5.
20
69330
3000
직접 μ™€μ„œ 라이트 μŠ€ν…Œμ΄μ§€ 5(Light Stage 5) μ„Έμ…˜μ— μ°Έκ°€ν–ˆμ–΄μš”.
01:12
This is a face-scanning sphere, with 156 white LEDs all around
21
72330
4000
이것이 156개의 백색 LEDκ°€ λ‹¬λ €μžˆλŠ” μ•ˆλ©΄ μŠ€μΊλ‹ μŠ€ν”Όμ–΄μž…λ‹ˆλ‹€.
01:16
that allow us to photograph her
22
76330
2000
사진을 μ°λŠ” λ™μ•ˆ
01:18
in a series of very controlled illumination conditions.
23
78330
3000
μ‘°λͺ… μƒνƒœλ₯Ό μ•„μ£Ό μ„Έλ°€ν•˜κ²Œ μ‘°μ •ν•  수 있죠.
01:21
And the lighting that we use these days looks something like this.
24
81330
3000
그리고 이 λ•Œ μ‚¬μš©ν–ˆλ˜ μ‘°λͺ…은 μ΄λž¬μŠ΅λ‹ˆλ‹€.
01:24
We shoot all of these photographs in about three seconds.
25
84330
2000
이 사진듀은 λͺ¨λ‘ 3초 λ§Œμ— 찍은 κ²ƒμž…λ‹ˆλ‹€.
01:26
And we basically capture enough information
26
86330
3000
μš°μ„  에밀리 μ–Όκ΅΄μ˜ 전체 μœ€κ³½μ—μ„œ μ„Έλ°€ν•œ λΆ€λΆ„κΉŒμ§€
01:29
with video projector patterns that drape over the contours of her face,
27
89330
4000
νŒŒμ•…ν•˜κΈ° μœ„ν•΄ λ‹€μ–‘ν•œ λΉ„λ””μ˜€ ν”„λ‘œμ ν„°μ˜ νŒ¨ν„΄κ³Ό
01:33
and different principle directions of light from the light stage,
28
93330
2000
라이트 μŠ€ν…Œμ΄μ§€μ˜ λ‹€μ–‘ν•œ μ‘°λͺ… κ°λ„λ‘œλΆ€ν„°
01:35
to figure out both the coarse-scale
29
95330
2000
μΆ©λΆ„ν•œ 정보λ₯Ό
01:37
and the fine-scale detail of her face.
30
97330
2000
λ½‘μ•„λƒ…λ‹ˆλ‹€
01:39
If we zoom in on this photograph right here,
31
99330
2000
μ§€κΈˆ λ³΄μ‹œλŠ” 사진을 ν™•λŒ€ν•΄λ³΄λ©΄
01:41
we can see it's a really nice photograph to have of her,
32
101330
2000
μ•„μ£Ό 쒋은 μ‚¬μ§„μž„μ„ μ•Œ 수 μžˆμŠ΅λ‹ˆλ‹€.
01:43
because she is lit from absolutely everywhere at the same time
33
103330
4000
에밀리 얼꡴이 λ™μ‹œμ— 골고루 빛을 λ°›μ•„μ„œ
01:47
to get a nice image of her facial texture.
34
107330
2000
μ–‘μ§ˆμ˜ μ•ˆλ©΄ 질감 이미지λ₯Ό 얻을 수 있기 λ•Œλ¬Έμž…λ‹ˆλ‹€.
01:49
And in addition, we've actually used polarizers on all the lights --
35
109330
3000
그리고 μ €ν¬λŠ” λͺ¨λ“  빛에 νŽΈκ΄‘κΈ°λ₯Ό μ‚¬μš©ν–ˆμŠ΅λ‹ˆλ‹€.
01:52
just like polarized sunglasses can block
36
112330
2000
λ„λ‘œμ˜ λˆˆλΆ€μ‹¬μ„ λ§‰μ•„μ£ΌλŠ”
01:54
the glare off of the road,
37
114330
2000
νŽΈκ΄‘ μ„ κΈ€λΌμŠ€μ²˜λŸΌ 말이죠.
01:56
polarizers can block the shine off of the skin,
38
116330
2000
νŽΈκ΄‘κΈ°κ°€ 피뢀에 λ“€μ–΄μ˜€λŠ” 빛을 차단해주기 λ•Œλ¬Έμ—
01:58
so we don't get all those specular reflections to take this map.
39
118330
3000
이 ν™”μƒμ—λŠ” λ°˜μ‚¬κ΄‘μ΄ μ—†μŠ΅λ‹ˆλ‹€.
02:01
Now, if we turn the polarizers around just a little bit,
40
121330
2000
저희가 νŽΈκ΄‘κΈ°μ˜ λ°©ν–₯을 쑰금만 λ°”κΎΈλ©΄
02:03
we can actually bring that specular reflection
41
123330
2000
사진에 ν”ΌλΆ€μ˜ λ°˜μ‚¬κ΄‘μ΄
02:05
of the skin back in,
42
125330
2000
μ°νž™λ‹ˆλ‹€.
02:07
and you can see she looks kind of shiny and oily at this point.
43
127330
3000
방금 λ²ˆλ“€κ±°λ¦¬λŠ” μ—λ°€λ¦¬μ˜ 얼꡴을 보싀 수 μžˆμ—ˆμ£ .
02:10
If you take the difference between these two images here,
44
130330
3000
두 μ΄λ―Έμ§€μ˜ 차이점을 ꡬ해보면
02:13
you can get an image lit from the entire sphere of light
45
133330
2000
μ—λ°€λ¦¬μ˜ ν”ΌλΆ€ ν‘œλ©΄μ—μ„œ λ°˜μ‚¬λ˜κ³  μžˆλŠ”
02:15
of just the shine off of Emily's skin.
46
135330
3000
μŠ€ν”Όμ–΄μ˜ λͺ¨λ“  빛이 λ‹΄κΈ΄ 이미지λ₯Ό 얻을 수 μžˆμŠ΅λ‹ˆλ‹€.
02:18
I don't think any photograph like this had ever been taken
47
138330
2000
μ•„λ§ˆ 저희가 ν•˜κΈ° μ „μ—λŠ” 이런 μ‹μœΌλ‘œ
02:20
before we had done this.
48
140330
2000
찍은 사진이 μ—†μ—ˆμ„ κ²ƒμž…λ‹ˆλ‹€.
02:22
And this is very important light to capture,
49
142330
3000
이 빛을 μž‘μ•„λ‚΄λŠ” 일은 μ•„μ£Ό μ€‘μš”ν•©λ‹ˆλ‹€.
02:25
because this is the light that reflects off the first surface of the skin.
50
145330
2000
ν”ΌλΆ€μ˜ ν‘œμΈ΅μ—μ„œ λ°˜μ‚¬λ˜λŠ” 빛이기 λ•Œλ¬Έμž…λ‹ˆλ‹€.
02:27
It doesn't get underneath the translucent
51
147330
2000
ν”ΌλΆ€ μ†μœΌλ‘œ ν‘μˆ˜λ˜μ—ˆλ‹€κ°€
02:29
layers of the skin and blur out.
52
149330
2000
μŠ€λ©°λ‚˜μ˜€λŠ” 빛이 μ•„λ‹ˆμ—μš”.
02:31
And, as a result, it's a very good cue
53
151330
2000
κ·Έ λ•Œλ¬Έμ— μš°λ¦¬λ“€μ΄ 가지고 μžˆλŠ” λͺ¨κ³΅μ˜ κ΅¬μ‘°λ‚˜
02:33
to the detailed shape of the skin-pore structure
54
153330
3000
μžμž˜ν•œ μ£Όλ¦„μ²˜λŸΌ μ§„μ§œ μ‚¬λžŒμœΌλ‘œ 보이게
02:36
and all of the fine wrinkles that all of us have,
55
156330
2000
ν•΄μ£ΌλŠ” νŠΉμ§•λ“€μ— λŒ€ν•΄
02:38
the things that actually make us look like real humans.
56
158330
2000
μžμ„Ένžˆ μ•Œλ €μ€λ‹ˆλ‹€.
02:40
So, if we use information that comes off of this specular reflection,
57
160330
4000
κ·Έλž˜μ„œ 기쑴의 μ•ˆλ©΄ μŠ€μΊ”μ—μ„œ 얻을 수 μžˆλŠ”
02:44
we can go from a traditional face scan
58
164330
2000
전체적인 윀곽과 κΈ°λ³Έ ν˜•νƒœ μœ„μ—
02:46
that might have the gross contours of the face and the basic shape,
59
166330
4000
λ°˜μ‚¬κ΄‘ μ΄λ―Έμ§€μ—μ„œ 얻을 수 μžˆλŠ”
02:50
and augment it with information
60
170330
2000
λͺ¨κ³΅ ꡬ쑰와 μžμž˜ν•œ 주름 λ“±μ˜
02:52
that puts in all of that skin pore structure and fine wrinkles.
61
172330
3000
정보λ₯Ό λ”ν–ˆμŠ΅λ‹ˆλ‹€.
02:55
And, even more importantly,
62
175330
2000
더 μ€‘μš”ν•œ 것은
02:57
since this is a photometric process that only takes three seconds to capture,
63
177330
3000
3λΆ„ 정도면 찍을 수 μžˆλŠ” 광도 μΈ‘μ • κ³Όμ •λ§Œ 거치면 λ˜λŠ”
03:00
we can shoot Emily
64
180330
2000
μž‘μ—…μ΄κΈ° λ•Œλ¬Έμ— 에밀리가
03:02
in just part of an afternoon,
65
182330
2000
μ˜€ν›„μ— 잠깐 μ‹œκ°„μ„ λ‚΄μ„œ
03:04
in many different facial poses and facial expressions.
66
184330
3000
λ‹€μ–‘ν•œ ν‘œμ •μ„ μ§€μ–΄μ£ΌκΈ°λ§Œ ν•˜λ©΄ λ©λ‹ˆλ‹€.
03:07
So, here you can see her moving her eyes around, moving her mouth around.
67
187330
3000
μ—¬κΈ° 에밀리가 λˆˆμ„ 움직이고, μž…μ„ μ›€μ§μ΄λŠ” 것을 보싀 수 있죠.
03:10
And these we're actually going to use to create a photo-real digital character.
68
190330
3000
이걸둜 μ‹€μ œ 포토리얼 디지털 캐릭터λ₯Ό λ§Œλ“€μ–΄ λ‚Ό κ²λ‹ˆλ‹€.
03:13
If you take a look at these scans that we have of Emily,
69
193330
4000
μš°λ¦¬κ°€ μŠ€μΊ”ν•œ 에밀리 사진을 λ³΄μ„Έμš”.
03:17
you can see that the human face does an enormous amount of amazing things
70
197330
3000
각기 λ‹€λ₯Έ μ–Όκ΅΄ ν‘œν˜„μ— λ”°λΌμ„œ μ‚¬λžŒμ˜ 얼꡴이
03:20
as it goes into different facial expressions.
71
200330
3000
ꡉμž₯히 λ†€λΌμš΄ 일을 ν•˜λŠ” 것이 보싀 수 μžˆμ–΄μš”.
03:23
You can see things. Not only the face shape changes,
72
203330
3000
μ–Όκ΅΄ ν˜•νƒœλ§Œ λ³€ν•˜λŠ” 게 μ•„λ‹ˆλΌ
03:26
but all sorts of different skin buckling and skin wrinkling occurs.
73
206330
4000
얼꡴을 찑그리고 주름이 생기고
03:30
You can see that the skin pore structure changes enormously
74
210330
4000
λͺ¨κ³΅ 쑰직이 μ—„μ²­λ‚˜κ²Œ λ³€ν•˜μ£ .
03:34
from stretched skin pores
75
214330
2000
λŠ˜μ–΄λ‚¬λ‹€κ°€
03:36
to the regular skin texture.
76
216330
2000
μ •μƒμœΌλ‘œ λŒμ•„μ˜€κ³ μš”.
03:38
You can see the furrows in the brow and how the microstructure changes there.
77
218330
3000
이마의 주름과 κ·Έ μ£Όλ¦„μ˜ 미세쑰직이 λ³€ν™”ν•˜λŠ” 것과
03:41
You can see muscles pulling down at flesh to bring her eyebrows down.
78
221330
4000
ν”ΌλΆ€μ˜ 근윑이 λˆˆμΉμ„ λ‚΄λ €λ‹ΉκΈ°λŠ” 것을 λ³Ό 수 μžˆμ„ κ²ƒμž…λ‹ˆλ‹€.
03:45
Her muscles bulging in her forehead when she winces like that.
79
225330
3000
λ³΄λŠ” κ²ƒμ²˜λŸΌ 움찔할 λ•ŒλŠ” μ•ž 이마의 근윑이 뢈거져 λ‚˜μ˜΅λ‹ˆλ‹€.
03:48
In addition to this kind of high-resolution geometry,
80
228330
3000
λͺ¨λ‘ μ‚¬μ§„κΈ°λ‘œ 찍은 이미지듀이기 λ•Œλ¬Έμ—
03:51
since it's all captured with cameras, we've got a great texture map to use for the face.
81
231330
4000
이런 μ’…λ₯˜μ˜ 고해상도 화상 외에 μ–Όκ΅΄ μ§ˆκ°μ„ κΈ°λ§‰νžˆκ²Œ ν‘œν˜„ν•  수 μžˆλŠ” 화상도 κ°–κ²Œ λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
03:55
And by looking at how the different color channels of the illumination,
82
235330
2000
그리고 λΉ¨κ°•, 초둝, νŒŒλž‘ μ„Έ 가지 μ‘°λͺ… 색상 μ±„λ„μ˜
03:57
the red and the green and the blue,
83
237330
2000
차이점을 μ‚΄νŽ΄λ³΄λ‹ˆ
03:59
diffuse the light differently,
84
239330
2000
빛을 λ‹€λ₯΄κ²Œ μ‚°λž€μ‹œν‚€κ³  μžˆλ”κ΅°μš”.
04:01
we can come up with a way of shading the skin on the computer.
85
241330
3000
이λ₯Ό μ°Έκ³ ν•΄μ„œ μ»΄ν“¨ν„°μ—μ„œ 피뢀에 μŒμ˜μ„ 쀄 수 μžˆλŠ” 방법을 κ³ μ•ˆν–ˆμ–΄μš”.
04:04
Then, instead of looking like a plaster mannequin,
86
244330
3000
κ·Έ 덕뢄에 이미지듀이 석고 λ§ˆλ„€ν‚Ήμ²˜λŸΌ 보이지 μ•Šκ³ 
04:07
it actually looks like it's made out of living human flesh.
87
247330
3000
μ§„μ§œ μ‚΄μ•„μžˆλŠ” μ‚¬λžŒμ˜ ν”ΌλΆ€μ²˜λŸΌ 보이죠.
04:10
And this is what we used
88
250330
2000
이것이 μš°λ¦¬κ°€
04:12
to give to the company Image Metrics
89
252330
2000
λ””μ§€ν„Έλ‘œ μ‘°ν•©ν•œ 에밀리λ₯Ό λ§Œλ“€ 수 μžˆλ„λ‘
04:14
to create a rigged, digital version of Emily.
90
254330
3000
이미지 λ©”νŠΈλ¦­μŠ€ 사에 보낸 κ²ƒλ“€μž…λ‹ˆλ‹€.
04:17
We're just seeing the coarse-scale geometry here.
91
257330
2000
μ§€κΈˆ 보고 계신 것은 λŒ€μΆ© 윀곽만 μžˆλŠ” 화상이긴 ν•˜μ§€λ§Œ
04:19
But they basically created a digital puppet of her,
92
259330
3000
사싀은 디지털 μΈν˜•μž…λ‹ˆλ‹€.
04:22
where you can pull on these various strings,
93
262330
2000
λ‹€μ–‘ν•œ 쀄을 λ‹ΉκΈ°λ©΄
04:24
and it actually moves her face in ways that are
94
264330
2000
κ·Έλ…€μ˜ 얼꡴이 쀄을 따라 움직이죠.
04:26
completely consistent with the scans that we took.
95
266330
2000
μš°λ¦¬κ°€ μŠ€μΊ”ν•œ 이미지와 μΌμΉ˜ν•©λ‹ˆλ‹€.
04:28
And, in addition to the coarse-scale geometry,
96
268330
2000
이 λŒ€κ°•μ˜ 윀곽만 μžˆλŠ” 화상에
04:30
they also used all of that detail
97
270330
2000
λͺ¨λ“  μ„ΈλΆ€ 사항을 λ”ν•΄μ„œ
04:32
to create a set of what are called "displacement maps"
98
272330
3000
μ›€μ§μ΄κ²Œλ„ ν•  수 μžˆλŠ” 일련의
04:35
that animate as well.
99
275330
3000
"λ””μŠ€ν”Œλ ˆμ΄μŠ€λ¨ΌνŠΈ 맡(Displacement map)"을 λ§Œλ“­λ‹ˆλ‹€.
04:38
These are the displacement maps here.
100
278330
2000
μ§€κΈˆ λ³΄μ‹œλŠ” 것이 λ””μŠ€ν”Œλ ˆμ΄μŠ€λ¨ΌνŠΈ λ§΅μž…λ‹ˆλ‹€.
04:40
And you can see those different wrinkles actually show up as she animates.
101
280330
3000
얼꡴이 μ›€μ§μ΄λ©΄μ„œ μ„œλ‘œ λ‹€λ₯Έ 주름이 μƒκΈ°λŠ” κ±° λ³΄μ΄μ‹œμ£ ?
04:43
So the next process was then to animate her.
102
283330
2000
κ·Έ λ‹€μŒ λ‹¨κ³„λŠ” 이 얼꡴을 μ›€μ§μ΄κ²Œ ν•˜λŠ” κ²ƒμž…λ‹ˆλ‹€.
04:45
We actually used one of her own performances to provide the source data.
103
285330
4000
μš°λ¦¬λŠ” κ·Έλ…€μ˜ μ—°κΈ° λ™μž‘μ„ μ†ŒμŠ€ λ°μ΄ν„°λ‘œ μ‚¬μš©ν–ˆμŠ΅λ‹ˆλ‹€.
04:49
So, by analyzing this video with computer vision techniques,
104
289330
3000
이 λ™μ˜μƒμ„ 컴퓨터 μ‹œκ° 기술둜 λΆ„μ„ν•΄μ„œ
04:52
they were able to drive the facial rig
105
292330
2000
μ»΄ν“¨ν„°λ‘œ ν‘œμ •μ„
04:54
with the computer-generated performance.
106
294330
2000
μ‘°ν•©ν•  수 있게 λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
04:56
So what you're going to see now, after this,
107
296330
2000
μ΄μ œλΆ€ν„° μ—¬λŸ¬λΆ„κ»˜ λ³΄μ—¬λ“œλ¦΄ 것은
04:58
is a completely photo-real digital face.
108
298330
2000
μ™„μ „νžˆ ν¬ν† λ¦¬μ–Όν•œ 디지털 μ–Όκ΅΄μž…λ‹ˆλ‹€.
05:00
We can turn the volume up a little bit if that's available.
109
300330
2000
κ°€λŠ₯ν•˜λ‹€λ©΄ μ†Œλ¦¬ 크기λ₯Ό ν‚€μ›Œμ£Όμ„Έμš”.
05:02
Emily: Image Metrics is a markerless, performance-driven animation company.
110
302330
4000
에밀리: 이미지 λ©”νŠΈλ¦­μŠ€λŠ” 마컀리슀(markerless) κΈ°μˆ μ„ μ‚¬μš©ν•œ μ—°κΈ°μž 기반 μ• λ‹ˆλ©”μ΄μ…˜ κΈ°μ—…μž…λ‹ˆλ‹€.
05:06
We specialize in high-quality facial animation
111
306330
3000
μ €ν¬λŠ” λΉ„λ””μ˜€ κ²Œμž„μ΄λ‚˜ μ˜ν™”μ— μ‚¬μš©ν•  수 μžˆλŠ”
05:09
for video games and films.
112
309330
2000
κ³ ν’ˆμ§ˆμ˜ μ•ˆλ©΄ μ• λ‹ˆλ©”μ΄μ…˜μ„ μ „λ¬ΈμœΌλ‘œ ν•©λ‹ˆλ‹€.
05:11
Image Metrics is a markerless, performance-driven animation company.
113
311330
4000
이미지 λ©”νŠΈλ¦­μŠ€λŠ” 마컀리슀(markerless) κΈ°μˆ μ„ μ‚¬μš©ν•œ μ—°κΈ°μž 기반 μ• λ‹ˆλ©”μ΄μ…˜ κΈ°μ—…μž…λ‹ˆλ‹€.
05:15
We specialize in high quality facial animation
114
315330
3000
μ €ν¬λŠ” λΉ„λ””μ˜€ κ²Œμž„μ΄λ‚˜ μ˜ν™”μ— μ‚¬μš©ν•  수 μžˆλŠ”
05:18
for video games and films.
115
318330
3000
κ³ ν’ˆμ§ˆμ˜ μ•ˆλ©΄ μ• λ‹ˆλ©”μ΄μ…˜μ„ μ „λ¬ΈμœΌλ‘œ ν•©λ‹ˆλ‹€.
05:21
Paul Debevec: So, if we break that down into layers, here's that diffuse component
116
321330
2000
폴 데베벑: 이것을 μ—¬λŸ¬ λ ˆμ΄μ–΄λ‘œ λΆ„λ¦¬ν•˜λ©΄
05:23
we saw in the first slide.
117
323330
2000
첫 μŠ¬λΌμ΄λ“œμ—μ„œ 보신 λΆ„μ‚° μ»΄ν¬λ„ŒνŠΈμž…λ‹ˆλ‹€.
05:25
Here is the specular component animating.
118
325330
2000
이것은 μ›€μ§μ΄λŠ” λ°˜μ‚¬κ΄‘ μ»΄ν¬λ„ŒνŠΈμ΄κ³ 
05:27
You can see all the wrinkles happening there.
119
327330
2000
μ—¬κΈ° μ£Όλ¦„μ§€λŠ” 것을 λ³Ό 수 있죠.
05:29
And there is the underlying wireframe mesh.
120
329330
5000
와이어 ν”„λ ˆμž„ 그물망도 μž…ν˜€λ΄€μŠ΅λ‹ˆλ‹€.
05:34
And that is Emily herself.
121
334330
2000
이건 μ—λ°€λ¦¬μ˜ λ³Έ μ–Όκ΅΄μž…λ‹ˆλ‹€.
05:36
Now, where are we going with this here?
122
336330
2000
μ €ν¬μ˜ λ‹€μŒ λͺ©ν‘œλŠ” λ­˜κΉŒμš”?
05:38
We've gone a little bit beyond Light Stage 5. This is Light Stage 6,
123
338330
4000
μ €ν¬λŠ” 라이트 μŠ€ν…Œμ΄μ§€ 5 μ—μ„œ 쑰금 더 λ‚˜κ°€λ΄€μŠ΅λ‹ˆλ‹€. λ³΄μ‹œλŠ” 것은 라이트 μŠ€ν…Œμ΄μ§€ 6 μž…λ‹ˆλ‹€.
05:42
and we're looking at taking this technology
124
342330
2000
μ—¬κΈ°μ„œλŠ” μ•žμ„œ μ†Œκ°œν•œ κΈ°μˆ μ„ 인체에
05:44
and applying it to whole human bodies.
125
344330
2000
μ μš©ν•˜λŠ” 연ꡬλ₯Ό ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€.
05:46
This is Bruce Lawmen, one of our researchers in the group,
126
346330
2000
이뢄은 μ—°κ΅¬μž 쀑 ν•œ 뢄인 브루슀 둜멘 μ”¨μΈλ°μš”.
05:48
who graciously agreed to get captured running in the Light Stage.
127
348330
3000
라이트 μŠ€ν…Œμ΄μ§€μ—μ„œ λ‹¬λ¦¬λŠ” λͺ¨μŠ΅μ„ 캑쳐할 수 μžˆλ„λ‘ ν•΄μ£Όμ…¨μ£ .
05:51
And let's take a look at a computer-generated version
128
351330
2000
컴퓨터가 λ§Œλ“€μ–΄λ‚Έ ν™˜κ²½μ—μ„œ 달리고 μžˆλŠ”
05:53
of Bruce, running in a new environment.
129
353330
2000
브루슀λ₯Ό λ³΄μ‹œμ£ .
06:01
And thank you very much.
130
361330
2000
κ°μ‚¬ν•©λ‹ˆλ‹€.
06:03
(Applause)
131
363330
1000
(λ°•μˆ˜)
이 μ›Ήμ‚¬μ΄νŠΈ 정보

이 μ‚¬μ΄νŠΈλŠ” μ˜μ–΄ ν•™μŠ΅μ— μœ μš©ν•œ YouTube λ™μ˜μƒμ„ μ†Œκ°œν•©λ‹ˆλ‹€. μ „ 세계 졜고의 μ„ μƒλ‹˜λ“€μ΄ κ°€λ₯΄μΉ˜λŠ” μ˜μ–΄ μˆ˜μ—…μ„ 보게 될 κ²ƒμž…λ‹ˆλ‹€. 각 λ™μ˜μƒ νŽ˜μ΄μ§€μ— ν‘œμ‹œλ˜λŠ” μ˜μ–΄ μžλ§‰μ„ 더블 ν΄λ¦­ν•˜λ©΄ κ·Έκ³³μ—μ„œ λ™μ˜μƒμ΄ μž¬μƒλ©λ‹ˆλ‹€. λΉ„λ””μ˜€ μž¬μƒμ— 맞좰 μžλ§‰μ΄ μŠ€ν¬λ‘€λ©λ‹ˆλ‹€. μ˜κ²¬μ΄λ‚˜ μš”μ²­μ΄ μžˆλŠ” 경우 이 문의 양식을 μ‚¬μš©ν•˜μ—¬ λ¬Έμ˜ν•˜μ‹­μ‹œμ˜€.

https://forms.gle/WvT1wiN1qDtmnspy7