TED2009
Ed Ulbrich: How Benjamin Button got his face
Ed Ulbrich 展示本杰明·巴顿的脸是怎么来的
Filmed:
Readability: 4.4
1,080,448 views
Ed Ulbrich，这位来自Digital Domain的数字特效牛人，解释一项获得奥斯卡奖的技术，使得他的团队能够为电影 本杰明·巴顿奇事 数字化的创造布拉德皮特年幼与老年时的面像。
Ed Ulbrich - Visual storyteller
Ed Ulbrich works at the leading edge of computer-generated visuals. On a recent project, filmmakers, artists, and technologists have been working at a breakthrough point where reality and digitally created worlds collide. Full bio
Ed Ulbrich works at the leading edge of computer-generated visuals. On a recent project, filmmakers, artists, and technologists have been working at a breakthrough point where reality and digitally created worlds collide. Full bio
Double-click the English transcript below to play the video.
00:18
I'm here today representing a team of artists and technologists and filmmakers
0
0
5000
今天我在这里代表了一队艺术家、技术专家和电影制作者
00:23
that worked together on a remarkable film project for the last four years.
1
5000
3000
在过去的四年里，他们在一起为一个了不起的电影项目工作。
00:26
And along the way they created a breakthrough in computer visualization.
2
8000
4000
在这一过程中，他们在计算机视觉特效做出了突破。
00:30
So I want to show you a clip of the film now.
3
12000
3000
所以我现在想为你们播放一段电影片段。
00:33
Hopefully it won't stutter.
4
15000
3000
但愿播放不会卡。
00:36
And if we did our jobs well, you won't know that we were even involved.
5
18000
3000
若是我们做得好的话，你们不会觉察到我们曾参与其中。
00:39
Voice (Video): I don't know how it's possible ...
6
21000
3000
电影内容：我不知道这怎么可能。。。
00:42
but you seem to have more hair.
7
24000
3000
但是看上去你的头发多了。
00:45
Brad Pitt: What if I told you that I wasn't getting older ...
8
27000
3000
本杰明·巴顿：如果我告诉你我没有变老。。。
00:48
but I was getting younger than everybody else?
9
30000
2000
却变得比比人年轻了会怎样？
00:53
I was born with some form of disease.
10
35000
3000
我生来就得了一种病。
00:56
Voice: What kind of disease?
11
38000
2000
声音：什么病？
00:58
BP: I was born old.
12
40000
2000
本杰明·巴顿：我生来年老。
01:01
Man: I'm sorry.
13
43000
2000
男声：抱歉。
01:03
BP: No need to be. There's nothing wrong with old age.
14
45000
3000
本杰明·巴顿：没必要。年老没有什么错。
01:08
Girl: Are you sick?
15
50000
2000
女声：你病了吗？
01:10
BP: I heard momma and Tizzy whisper,
16
52000
3000
本杰明·巴顿：我听到妈妈和Tizzy偷偷说话，
01:13
and they said I was gonna die soon.
17
55000
2000
他们说我就快要死了。
01:15
But ... maybe not.
18
57000
3000
但是。。。或许不会。
01:18
Girl: You're different than anybody I've ever met.
19
60000
3000
女声：你同我见过的所有人都不一样。
01:22
BB: There were many changes ...
20
64000
3000
本杰明·巴顿：变化了好多。。。
01:25
some you could see, some you couldn't.
21
67000
3000
一些你能看到，一些你不能。
01:28
Hair started growing in all sorts of places,
22
70000
3000
毛发开始在身体的各个地方生长，
01:31
along with other things.
23
73000
3000
一些别的东西也是。
01:34
I felt pretty good, considering.
24
76000
3000
我感觉相当好。
01:38
Ed Ulbrich: That was a clip from "The Curious Case of Benjamin Button."
25
80000
4000
Ed Ulbrich：刚刚播放的是来自《本杰明巴顿奇事》的电影片段。
01:42
Many of you, maybe you've seen it or you've heard of the story,
26
84000
4000
你们中的许多人可能已经看过或者听说过这个故事。
01:46
but what you might not know
27
88000
2000
但是你或许有所不知的是
01:48
is that for nearly the first hour of the film,
28
90000
2000
在电影的接近一小时里，
01:50
the main character, Benjamin Button, who's played by Brad Pitt,
29
92000
3000
由布拉德皮特扮演的主角，本杰明巴顿
01:53
is completely computer-generated from the neck up.
30
95000
3000
他脖子以上的部分完全是由计算机生成的。
01:56
Now, there's no use of prosthetic makeup
31
98000
3000
注意，我们没有使用假体化妆
01:59
or photography of Brad superimposed over another actor's body.
32
101000
3000
或者将布拉德的照片附加到另一个演员的身体上。
02:02
We've created a completely digital human head.
33
104000
3000
我们创造了一个完全数字的人类头部。
02:05
So I'd like to start with a little bit of history on the project.
34
107000
3000
现在我想开始讲一点这个项目的历史。
02:08
This is based on an F. Scott Fitzgerald short story.
35
110000
2000
这是基于菲兹杰拉德的一部短篇故事。
02:10
It's about a man who's born old and lives his life in reverse.
36
112000
3000
讲的是一个生下来就很老然后过着相反的生活。
02:13
Now, this movie has floated around Hollywood
37
115000
2000
现在，这个电影已经在好莱坞发行了
02:15
for well over half a century,
38
117000
2000
半个世纪了
02:17
and we first got involved with the project in the early '90s,
39
119000
3000
在九十年代早期，我们第一次参与了这个项目
02:20
with Ron Howard as the director.
40
122000
2000
当时的导演是朗·霍华德
02:22
We took a lot of meetings and we seriously considered it.
41
124000
3000
我们开了很多会并认真的考虑了
02:25
But at the time we had to throw in the towel.
42
127000
2000
但是当时我们不得不投降认输
02:27
It was deemed impossible.
43
129000
2000
当时被认为是不可能的。
02:29
It was beyond the technology of the day to depict a man aging backwards.
44
131000
4000
刻画一个人从老到年轻，这超越了当时的技术能力。
02:33
The human form, in particular the human head,
45
135000
3000
人类的构型，尤其是头部，
02:36
has been considered the Holy Grail of our industry.
46
138000
3000
被看作是我们工业里的圣杯。
02:39
The project came back to us about a decade later,
47
141000
3000
十年后这个项目由回到我们这里，
02:42
and this time with a director named David Fincher.
48
144000
3000
这一回导演的名字是大卫·芬奇
02:45
Now, Fincher is an interesting guy.
49
147000
3000
芬奇是个有趣的家伙。
02:48
David is fearless of technology,
50
150000
2000
他无惧于技术，
02:50
and he is absolutely tenacious.
51
152000
2000
并且绝对固执。
02:52
And David won't take "no."
52
154000
2000
并且大卫不会接受“不”。
02:54
And David believed, like we do in the visual effects industry,
53
156000
3000
大卫相信，就像我们对视觉特效工业的观点一样，
02:57
that anything is possible
54
159000
3000
没有不可能
03:00
as long as you have enough time, resources and, of course, money.
55
162000
3000
前提是你有足够的时间，资源，当然，还有钱
03:03
And so David had an interesting take on the film,
56
165000
4000
因此大卫有兴趣接手这部电影，
03:07
and he threw a challenge at us.
57
169000
3000
并且给我们抛来一个挑战。
03:10
He wanted the main character of the film to be played
58
172000
3000
他希望电影中的主角
03:13
from the cradle to the grave by one actor.
59
175000
2000
从摇篮里出来一直到进入坟墓，都由一个演员来演。
03:15
It happened to be this guy.
60
177000
2000
刚好是这个人。
03:17
We went through a process of elimination and a process of discovery
61
179000
3000
我们经历了削减和发现的过程
03:20
with David, and we ruled out, of course, swapping actors.
62
182000
3000
同大卫一道，当然，我们放弃了换演员的想法。
03:23
That was one idea: that we would have different actors,
63
185000
3000
那个想法就是：我们会有不同的演员，
03:26
and we would hand off from actor to actor.
64
188000
2000
并且我们会用一个又一个演员。
03:28
We even ruled out the idea of using makeup.
65
190000
2000
我们划掉了使用化妆的想法。
03:30
We realized that prosthetic makeup just wouldn't hold up,
66
192000
3000
我们意识到假体化妆就是没法做得真。
03:33
particularly in close-up.
67
195000
2000
特别是近看的时候。
03:35
And makeup is an additive process. You have to build the face up.
68
197000
3000
而且化妆是一个额外的步骤。 你不得不在脸的外边来化。
03:38
And David wanted to carve deeply into Brad's face
69
200000
3000
大卫想让皱纹深深的刻在布拉德的脸上
03:41
to bring the aging to this character.
70
203000
2000
以显示出这个角色的年纪变化。
03:43
He needed to be a very sympathetic character.
71
205000
2000
他需要一个非常的意气相投的人物。
03:45
So we decided to cast a series of little people
72
207000
3000
所以我们决定拍摄一系列的小人物
03:48
that would play the different bodies of Benjamin
73
210000
3000
他们扮演本杰明
03:51
at the different increments of his life
74
213000
2000
在不同时候的不同的身体
03:53
and that we would in fact create a computer-generated version of Brad's head,
75
215000
3000
并且我们事实上会创造一个计算机生成的布拉德的头部。
03:56
aged to appear as Benjamin,
76
218000
2000
随本杰明年纪而变化，
03:58
and attach that to the body of the real actor.
77
220000
3000
并将它附到真的演员身体上。
04:01
Sounded great.
78
223000
2000
听上去很棒。
04:03
Of course, this was the Holy Grail of our industry,
79
225000
3000
当然，这曾经是我们这一行离得圣杯，
04:06
and the fact that this guy is a global icon didn't help either,
80
228000
3000
事实上布拉德作为一个全球符号也没能帮上一把，
04:09
because I'm sure if any of you ever stand in line at the grocery store,
81
231000
3000
因为我很确信如果你们任何人站成一行在杂货店里，
04:12
you know -- we see his face constantly.
82
234000
3000
你知道，我们总是看到他的脸。
04:15
So there really was no tolerable margin of error.
83
237000
2000
所以这里边没有容错的空间。
04:17
There were two studios involved: Warner Brothers and Paramount.
84
239000
3000
华纳兄弟和派拉蒙参与在其中。
04:20
And they both believed this would make an amazing film, of course,
85
242000
3000
他们都相信这无疑会是一个令人惊奇的电影
04:23
but it was a very high-risk proposition.
86
245000
3000
但是它也是一个非常高风险的提议。
04:26
There was lots of money and reputations at stake.
87
248000
3000
很多的钱与声誉都处在危险关头。
04:29
But we believed that we had a very solid methodology
88
251000
3000
我们相信我们有一个非常坚实的方法
04:32
that might work ...
89
254000
3000
可能管用。。。
04:35
But despite our verbal assurances,
90
257000
3000
但是无论我们如何口头承诺，
04:38
they wanted some proof.
91
260000
2000
他们要一些证明。
04:40
And so, in 2004, they commissioned us to do a screen test of Benjamin.
92
262000
3000
为此，在2004年，他们委托我们做一次本杰明的试镜。
04:43
And we did it in about five weeks.
93
265000
3000
我们差不多五周后做给他们看。
04:46
But we used lots of cheats and shortcuts.
94
268000
3000
但是我们在其中参了好多假并走了捷径。
04:49
We basically put something together to get through the meeting.
95
271000
3000
基本上我们把一些东西搁了一块儿就通过了会议。
04:52
I'll roll that for you now. This was the first test for Benjamin Button.
96
274000
3000
我现在把那些拿出来给你们看。 这是本杰明巴顿的第一个测试。
04:55
And in here, you can see, that's a computer-generated head --
97
277000
3000
然后在这里，你肯一看到，那是一个计算机生成的头部。
04:58
pretty good -- attached to the body of an actor.
98
280000
3000
相当不错。附到演员的身体后的样子。
05:01
And it worked. And it gave the studio great relief.
99
283000
3000
这个成了。 制片厂松了一口气。
05:04
After many years of starts and stops on this project,
100
286000
3000
在这个项目拍拍停停好多年，
05:07
and making that tough decision,
101
289000
3000
并做了艰难的选择后，
05:10
they finally decided to greenlight the movie.
102
292000
3000
他们最终决定为这个电影开绿灯。
05:13
And I can remember, actually, when I got the phone call to congratulate us,
103
295000
3000
我可以记起来，事实上，但我收到祝贺我们的电话，
05:16
to say the movie was a go,
104
298000
2000
说电影要拍了的时候，
05:18
I actually threw up.
105
300000
2000
我其实是一团糟。
05:20
(Laughter)
106
302000
2000
（笑声）
05:22
You know, this is some tough stuff.
107
304000
2000
你知道，这是一些艰难的东西。
05:24
So we started to have early team meetings,
108
306000
3000
然后我们开始了早期的团队会议，
05:27
and we got everybody together,
109
309000
2000
并且把所有人聚起来，
05:29
and it was really more like therapy in the beginning,
110
311000
3000
开始的时候更像是治疗，
05:32
convincing each other and reassuring each other that we could actually undertake this.
111
314000
3000
得相互说服、保证对方说我们确实能承担这些。
05:35
We had to hold up an hour of a movie with a character.
112
317000
3000
我们得支撑一部单人物持续一小时的电影
05:38
And it's not a special effects film; it has to be a man.
113
320000
3000
而且他并不是一部特效电影；中间得有一个人。
05:41
We really felt like we were in a -- kind of a 12-step program.
114
323000
3000
我们觉得自己就好像是在---某种戒瘾过程中。
05:44
And of course, the first step is: admit you've got a problem. (Laughter)
115
326000
3000
当然，第一步是：承认自己有一个问题。
05:48
So we had a big problem:
116
330000
2000
我们有一个大问题。
05:50
we didn't know how we were going to do this.
117
332000
3000
我们不知道我们该怎样去做。
05:53
But we did know one thing.
118
335000
2000
但我们知道一件事。
05:55
Being from the visual effects industry,
119
337000
3000
在视觉特效工业里，
05:58
we, with David, believed that we now had enough time,
120
340000
3000
我们，连同大卫，相信我们现在有足够的时间，
06:01
enough resources, and, God, we hoped we had enough money.
121
343000
3000
足够的资源，然后，天哪，我们希望我们有足够的钱。
06:04
And we had enough passion to will the processes and technology into existence.
122
346000
5000
并且我们有足够的激情去用意志趋势工序与技术变成实际。
06:09
So, when you're faced with something like that,
123
351000
2000
所以，当你面对一些这样的事情时，
06:11
of course you've got to break it down.
124
353000
2000
当然你会把它分块儿。
06:13
You take the big problem and you break it down into smaller pieces
125
355000
2000
你取一个大问题然后把它分成几个小问题
06:15
and you start to attack that.
126
357000
1000
然后开始攻破。
06:16
So we had three main areas that we had to focus on.
127
358000
2000
我们有三个主要的需要专注的地方。
06:18
We needed to make Brad look a lot older --
128
360000
2000
我们需要让布拉德看上去老许多。
06:20
needed to age him 45 years or so.
129
362000
2000
我们需要他差不多45岁的样子。
06:22
And we also needed to make sure that we could take Brad's idiosyncrasies,
130
364000
6000
我们也需要确保我们可以抓住布拉德的特殊癖好行为，
06:28
his little tics, the little subtleties that make him who he is
131
370000
2000
他的小抽搐，那些能体现他的细微之处
06:30
and have that translate through our process
132
372000
2000
并将它们转移到我们的处理过程中
06:32
so that it appears in Benjamin on the screen.
133
374000
3000
使得它出现在银幕上的本杰明中。
06:35
And we also needed to create a character
134
377000
2000
我们还需要创造一个角色
06:37
that could hold up under, really, all conditions.
135
379000
3000
他可以支撑起所有情况。
06:40
He needed to be able to walk in broad daylight,
136
382000
2000
他得能够行走在大白天，
06:42
at nighttime, under candlelight,
137
384000
3000
晚上，烛光中，
06:45
he had to hold an extreme close-up,
138
387000
2000
他得能够撑住大特写镜头，
06:47
he had to deliver dialogue,
139
389000
1000
他得能够传递对话，
06:48
he had to be able to run, he had to be able to sweat,
140
390000
2000
他得会跑，出汗，
06:50
he had to be able to take a bath, to cry,
141
392000
2000
他还得会洗澡，哭泣，
06:52
he even had to throw up.
142
394000
1000
他甚至得会呕吐。
06:53
Not all at the same time --
143
395000
1000
当然不是同时做这些事情。
06:54
but he had to, you know, do all of those things.
144
396000
2000
但是他得会，你知道，做所有这些事情。
06:56
And the work had to hold up for almost the first hour of the movie.
145
398000
3000
并且这些工作得支撑电影的差不多前一个小时。
06:59
We did about 325 shots.
146
401000
2000
我们拍摄了325个镜头
07:01
So we needed a system that would allow Benjamin
147
403000
3000
因此我们需要一个系统能够让本杰明
07:04
to do everything a human being can do.
148
406000
3000
去做任何人可以做的事情。
07:07
And we realized that there was a giant chasm
149
409000
3000
我们意识到一个大分歧
07:10
between the state of the art of technology in 2004
150
412000
3000
出现在2004年的技术艺术水平
07:13
and where we needed it to be.
151
415000
2000
和我们的愿望之间。
07:15
So we focused on motion capture.
152
417000
3000
因此我们集中在运动捕捉。
07:18
I'm sure many of you have seen motion capture.
153
420000
2000
我相信你们中许多人已经看过运动捕捉了。
07:20
The state of the art at the time
154
422000
2000
当时的工艺水平
07:22
was something called marker-based motion capture.
155
424000
2000
叫做基于标记的动作捕捉。
07:24
I'll give you an example here.
156
426000
1000
这里我给你们举一个例子。
07:25
It's basically the idea of, you wear a leotard,
157
427000
2000
想法基本上就是，你穿一个连衣裤，
07:27
and they put some reflective markers on your body,
158
429000
2000
然后安放一些反光标志
07:29
and instead of using cameras,
159
431000
2000
用来替换摄像机的，
07:31
there're infrared sensors around a volume,
160
433000
2000
是围绕在一个空间内的红外感应传感器
07:33
and those infrared sensors track the three-dimensional position
161
435000
2000
那些红外传感器实时地跟踪
07:35
of those markers in real time.
162
437000
2000
那些标记的空间位置
07:37
And then animators can take the data of the motion of those markers
163
439000
3000
然后动画师收集这些数据
07:40
and apply them to a computer-generated character.
164
442000
2000
并应用到计算机生成的人物中。
07:42
You can see the computer characters on the right
165
444000
3000
你可以看到右边的计算机人物
07:45
are having the same complex motion as the dancers.
166
447000
3000
正做着着同舞蹈者相同的复杂运动。
07:48
But we also looked at numbers of other films at the time
167
450000
2000
与此同时我们也关注其他的
07:50
that were using facial marker tracking,
168
452000
2000
运用脸部捕捉技术的电影
07:52
and that's the idea of putting markers on the human face
169
454000
2000
将标志放在脸部
07:54
and doing the same process.
170
456000
1000
进行同样的处理
07:55
And as you can see, it gives you a pretty crappy performance.
171
457000
4000
正如你所看到的，这种技术所生成的画面相当糟糕
07:59
That's not terribly compelling.
172
461000
3000
这并不十分引人注目。
08:02
And what we realized
173
464000
2000
我们意识到
08:04
was that what we needed
174
466000
1000
我们所需要的
08:05
was the information that was going on between the markers.
175
467000
2000
是那些在这些标志点之间的信息
08:07
We needed the subtleties of the skin.
176
469000
3000
我们需要皮肤的细节
08:10
We needed to see skin moving over muscle moving over bone.
177
472000
3000
我们需要透过皮肤看到肌肉和骨骼的运动
08:13
We needed creases and dimples and wrinkles and all of those things.
178
475000
2000
我们需要皱纹，酒窝之类的
08:15
Our first revelation was to completely abort and walk away from
179
477000
3000
我们第一件要做的事就是抛弃现今所用的技术
08:18
the technology of the day, the status quo, the state of the art.
180
480000
3000
这一天的技术，现状，最先进的。
08:21
So we aborted using motion capture.
181
483000
3000
所以我们放弃了动作捕捉
08:24
And we were now well out of our comfort zone,
182
486000
3000
我们离开了我们所熟悉的领域
08:27
and in uncharted territory.
183
489000
2000
进入了从未涉及过的新领域
08:29
So we were left with this idea
184
491000
3000
我们进入了一个技术上的难点
08:32
that we ended up calling "technology stew."
185
494000
3000
我们结束了通话“技术炖。”
08:35
We started to look out in other fields.
186
497000
2000
我们开始在其他领域需求帮助
08:37
The idea was that we were going to find
187
499000
3000
我们相信我们会找到我们所需要的技术
08:40
nuggets or gems of technology
188
502000
2000
金块或技术宝石
08:42
that come from other industries like medical imaging,
189
504000
2000
这项技术可能是从其他领域， 例如医药
08:44
the video game space,
190
506000
1000
或是家庭游戏机
08:45
and re-appropriate them.
191
507000
2000
或是重新调整他们
08:47
And we had to create kind of a sauce.
192
509000
3000
或者我们需要一项全新的技术
08:50
And the sauce was code in software
193
512000
3000
这项技术可以编写成一个软件
08:53
that we'd written to allow these disparate pieces of technology
194
515000
3000
允许我们将这些零散的信息组合在一起
08:56
to come together and work as one.
195
518000
2000
走到一起，齐心协力。
08:58
Initially, we came across some remarkable research
196
520000
2000
起初，我们遇见一些研究
09:00
done by a gentleman named Dr. Paul Ekman in the early '70s.
197
522000
3000
由Paul在70年代早期得到的
09:03
He believed that he could, in fact,
198
525000
3000
他认为 他可以将人类的面部表情归类
09:06
catalog the human face.
199
528000
2000
目录中的人脸。
09:08
And he came up with this idea of Facial Action Coding System, or FACS.
200
530000
3000
他设计了面部动作编码系统
09:11
He believed that there were 70 basic poses
201
533000
3000
他认为有10个基本的面部表情
09:14
or shapes of the human face,
202
536000
3000
人类面对或形状
09:17
and that those basic poses or shapes of the face
203
539000
3000
借由这些动作去构成无数种可能
09:20
can be combined to create infinite possibilities
204
542000
3000
它们可以结合起来，创造无限的可能性
09:23
of everything the human face is capable of doing.
205
545000
2000
一切人类面对的就是这样做的能力。
09:25
And of course, these transcend age, race, culture, gender.
206
547000
3000
这些全部不受年龄 种族 文化 性别的限制
09:28
So this became the foundation of our research as we went forward.
207
550000
4000
这成为我们继续的基石
09:32
And then we came across some remarkable technology
208
554000
3000
即接着我们遇到了一些卓越的科技
09:35
called Contour.
209
557000
1000
被称作Contour
09:36
And here you can see a subject having phosphorus makeup
210
558000
3000
你可以看到这个人的面部 具有磷 标记
09:39
stippled on her face.
211
561000
2000
点刻在她的脸上。
09:41
And now what we're looking at is really creating a surface capture
212
563000
3000
我们现在说看到的是一个真实面部捕捉
09:44
as opposed to a marker capture.
213
566000
2000
而不是那种标记捕捉
09:46
The subject stands in front of a computer array of cameras,
214
568000
2000
它站于一组由电脑驱动的相机阵列前
09:48
and those cameras can, frame-by-frame,
215
570000
2000
这些相机将会准确的描绘出物体的运动
09:50
reconstruct the geometry of exactly what the subject's doing at the moment.
216
572000
3000
重建几何正是这一主题的目前做的事情。
09:53
So, effectively, you get 3D data in real time of the subject.
217
575000
5000
我们可一有效的获得物体在3D空间的运动数据
09:58
And if you look in a comparison,
218
580000
3000
对比下这两种技术
10:01
on the left, we see what volumetric data gives us
219
583000
3000
在左侧，我们看到的数据给了我们什么容积
10:04
and on the right you see what markers give us.
220
586000
2000
并在右边你看到什么标记给我们。
10:07
So, clearly, we were in a substantially better place for this.
221
589000
2000
显而易见，这种技术是多么优越了
10:09
But these were the early days of this technology,
222
591000
2000
但是这还只是这项技术的雏形，
10:11
and it wasn't really proven yet.
223
593000
2000
还没有被完全证实。
10:13
We measure complexity and fidelity of data
224
595000
2000
但是，我们可以对比多边形定点个数做个比较。
10:15
in terms of polygonal count.
225
597000
2000
在多边形数计算。
10:17
And so, on the left, we were seeing 100,000 polygons.
226
599000
3000
左侧的是100，000个顶点
10:20
We could go up into the millions of polygons.
227
602000
2000
右边这个却已经打到了上亿个顶点
10:22
It seemed to be infinite.
228
604000
2000
或者可以认为是无限个
10:24
This was when we had our "Aha!"
229
606000
2000
这令我们豁然开朗
10:26
This was the breakthrough.
230
608000
1000
这是我们这个项目的一个中重大突破啊
10:27
This is when we're like, "OK, we're going to be OK,
231
609000
2000
这令我们有一种我们可以完成这部电影的信心了
10:29
This is actually going to work."
232
611000
1000
这一定会成功的
10:30
And the "Aha!" was, what if we could take Brad Pitt,
233
612000
4000
和“一哈！”是，如果我们可以采取布拉德皮特，
10:34
and we could put Brad in this device,
234
616000
3000
我们可以把布拉德本装置，
10:37
and use this Contour process,
235
619000
2000
并利用这一轮廓的过程中，
10:39
and we could stipple on this phosphorescent makeup
236
621000
2000
我们可以在这个点画磷光化妆
10:41
and put him under the black lights,
237
623000
1000
并把他下黑灯，
10:42
and we could, in fact, scan him in real time
238
624000
3000
我们可以，事实上，他在实时扫描
10:45
performing Ekman's FACS poses.
239
627000
2000
表演埃克曼的流式细胞仪构成。
10:47
Right? So, effectively,
240
629000
2000
看 非常有效
10:49
we ended up with a 3D database
241
631000
2000
我们最终完成了一个3D数据库
10:51
of everything Brad Pitt's face is capable of doing.
242
633000
3000
包含了所有Brad Pitt 的所有表情
10:54
(Laughter)
243
636000
2000
大笑
10:56
From there, we actually carved up those faces
244
638000
3000
这里， 我们实际上是分割了这些面部表情
10:59
into smaller pieces and components of his face.
245
641000
3000
分解为许多组成部分
11:02
So we ended up with literally thousands and thousands and thousands of shapes,
246
644000
3000
我们获得了上千种形状
11:05
a complete database of all possibilities
247
647000
3000
一个他面部所能做到的各种表情的数据库
11:08
that his face is capable of doing.
248
650000
3000
他面对的就是这样做的能力。
11:11
Now, that's great, except we had him at age 44.
249
653000
3000
这一切看起来都很不错， 不过这是他44岁的模样
11:14
We need to put another 40 years on him at this point.
250
656000
3000
我们需要将这个年龄加上40岁
11:17
We brought in Rick Baker,
251
659000
2000
我们于是请来了Rick Baker,
11:19
and Rick is one of the great makeup and special effects gurus
252
661000
2000
他是一名强力的化妆和特效天才，在电影行业中。
11:21
of our industry.
253
663000
1000
我们的工业。
11:22
And we also brought in a gentleman named Kazu Tsuji,
254
664000
3000
我们还有Kazu suji
11:25
and Kazu Tsuji is one of the great photorealist sculptors of our time.
255
667000
3000
Kazu 是一名非常好的动态光影建模师
11:28
And we commissioned them to make a maquette,
256
670000
3000
我们的人任务就是做一个模型
11:31
or a bust, of Benjamin.
257
673000
2000
或是 毁了他 本杰明
11:33
So, in the spirit of "The Great Unveiling" -- I had to do this --
258
675000
3000
因此，在“大揭幕精神” - 我不得不这样做
11:36
I had to unveil something.
259
678000
2000
我已经推出的东西。
11:38
So this is Ben 80.
260
680000
2000
这是ben 80岁的样子
11:40
We created three of these:
261
682000
2000
我们做了三个模型
11:42
there's Ben 80, there's Ben 70, there's Ben 60.
262
684000
2000
分别是本 80 70 60
11:44
And this really became the template for moving forward.
263
686000
3000
这是我们继续的模板
11:47
Now, this was made from a life cast of Brad.
264
689000
2000
现在，这是从一个生命铸造的布拉德。
11:49
So, in fact, anatomically, it is correct.
265
691000
3000
因此，事实上，在解剖学上，这是正确的。
11:52
The eyes, the jaw, the teeth:
266
694000
3000
的眼睛，下巴，牙齿...
11:55
everything is in perfect alignment with what the real guy has.
267
697000
3000
一切都是在完美的路线是什么真正的家伙。
11:58
We have these maquettes scanned into the computer
268
700000
2000
我们这些maquettes扫描进电脑
12:00
at very high resolution --
269
702000
2000
在非常高的分辨率。
12:02
enormous polygonal count.
270
704000
2000
巨大的多边形数。
12:04
And so now we had three age increments of Benjamin
271
706000
4000
所以现在我们有三个年龄递增本杰明
12:08
in the computer.
272
710000
2000
在计算机中。
12:10
But we needed to get a database of him doing more than that.
273
712000
3000
但是，我们必须找到他的数据库做不止于此。
12:13
We went through this process, then, called retargeting.
274
715000
3000
我们经历了这一过程，那么，所谓的重新定向。
12:16
This is Brad doing one of the Ekman FACS poses.
275
718000
2000
这是布拉德埃克曼流式细胞仪做的一个姿势。
12:18
And here's the resulting data that comes from that,
276
720000
3000
这里的结果数据来自该来了，
12:21
the model that comes from that.
277
723000
2000
该模型从该来。
12:23
Retargeting is the process of transposing that data
278
725000
3000
和重定目标的过程是数据的移调
12:26
onto another model.
279
728000
2000
到另一个模型。
12:28
And because the life cast, or the bust -- the maquette -- of Benjamin
280
730000
3000
而且因为生活投，或胸部 - 在maquette - 本雅明
12:31
was made from Brad,
281
733000
2000
是从布拉德，
12:33
we could transpose the data of Brad at 44
282
735000
3000
我们可以在44转布拉德数据
12:36
onto Brad at 87.
283
738000
2000
在87到布拉德。
12:38
So now, we had a 3D database of everything Brad Pitt's face can do
284
740000
3000
所以，现在，我们有一个三维数据库的一切布拉德皮特的脸可以做
12:41
at age 87, in his 70s and in his 60s.
285
743000
4000
87岁的他70多岁，在他60岁。
12:45
Next we had to go into the shooting process.
286
747000
3000
下一步，我们已进入了拍摄过程。
12:48
So while all that's going on,
287
750000
1000
因此，尽管所有这回事，
12:49
we're down in New Orleans and locations around the world.
288
751000
2000
我们下来在新奥尔良和世界各地的位置。
12:51
And we shot our body actors,
289
753000
2000
我们的身体，我们拍摄的演员，
12:53
and we shot them wearing blue hoods.
290
755000
2000
我们向他们拍摄身穿蓝色头巾。
12:55
So these are the gentleman who played Benjamin.
291
757000
2000
因此，这是绅士玩本杰明。
12:57
And the blue hoods helped us with two things:
292
759000
2000
和蓝盖帮我们两件事情：
12:59
one, we could easily erase their heads;
293
761000
2000
1，我们可以很容易抹掉他们的头上;
13:01
and we also put tracking markers on their heads
294
763000
2000
我们也把他们的头标记跟踪
13:03
so we could recreate the camera motion
295
765000
2000
这样我们就可以重新相机的动作
13:05
and the lens optics from the set.
296
767000
2000
从镜头的光学设置。
13:07
But now we needed to get Brad's performance to drive our virtual Benjamin.
297
769000
3000
但现在我们需要得到布拉德的表现，以推动我们的虚拟本杰明。
13:10
And so we edited the footage that was shot on location
298
772000
2000
因此，我们编辑了这是拍摄画面上的位置
13:12
with the rest of the cast and the body actors
299
774000
3000
与其他演员和演员的身体
13:15
and about six months later
300
777000
2000
约6个月后
13:17
we brought Brad onto a sound stage in Los Angeles
301
779000
3000
我们带来了布拉德到一个在洛杉矶的声场
13:20
and he watched on the screen.
302
782000
3000
他看着屏幕上
13:23
His job, then, was to become Benjamin.
303
785000
2000
当时他的工作成为本杰明。
13:25
And so we looped the scenes.
304
787000
1000
因此，我们循环的场景。
13:26
He watched again and again.
305
788000
1000
他一遍又一遍。
13:27
We encouraged him to improvise.
306
789000
2000
我们鼓励他即兴。
13:29
And he took Benjamin into interesting and unusual places
307
791000
3000
他带成有趣和不寻常的地方本杰明
13:32
that we didn't think he was going to go.
308
794000
2000
我们不认为他会去。
13:34
We shot him with four HD cameras
309
796000
2000
我们打到了他与4高清摄像机
13:36
so we'd get multiple views of him
310
798000
1000
所以我们会得到他的多个视图
13:37
and then David would choose the take of Brad being Benjamin
311
799000
3000
然后戴维会选择利用被本杰明布拉德
13:40
that he thought best matched the footage
312
802000
3000
他认为最匹配的镜头
13:43
with the rest of the cast.
313
805000
1000
同其他演员。
13:44
From there we went into a process called image analysis.
314
806000
3000
从那里我们去到一个名为图像分析过程。
13:47
And so here, you can see again, the chosen take.
315
809000
3000
所以在这里，你可以再次看到，所选择的需要。
13:50
And you are seeing, now, that data being transposed on to Ben 87.
316
812000
3000
我们看到，现在，该数据被调换到本87。
13:53
And so, what's interesting about this is
317
815000
3000
因此，有趣的是这
13:56
we used something called image analysis,
318
818000
2000
我们使用一种叫做图像分析，
13:58
which is taking timings from different components of Benjamin's face.
319
820000
3000
它正在从本雅明的脸不同部分的时间安排。
14:01
And so we could choose, say, his left eyebrow.
320
823000
3000
所以我们可以选择，例如，他的左眼眉。
14:04
And the software would tell us that, well,
321
826000
2000
而且，软件会告诉我们，好，
14:06
in frame 14 the left eyebrow begins to move from here to here,
322
828000
2000
在14帧的左眼眉开始从这里到这里，
14:08
and it concludes moving in frame 32.
323
830000
2000
并得出结论朝框架32。
14:10
And so we could choose numbers of positions on the face
324
832000
2000
因此，我们可以选择的职位数量在脸上
14:12
to pull that data from.
325
834000
2000
拉从数据。
14:14
And then, the sauce I talked about with our technology stew --
326
836000
2000
然后，我谈酱油与我们的技术炖，
14:16
that secret sauce was, effectively, software that allowed us to
327
838000
3000
这是秘密酱油，有效，使我们的软件
14:19
match the performance footage of Brad
328
841000
3000
布拉德性能相匹配的镜头
14:22
in live action with our database of aged Benjamin,
329
844000
4000
与我们的老年生活本杰明数据库的行动，
14:26
the FACS shapes that we had.
330
848000
2000
流式细胞仪的形状，我们有。
14:28
On a frame-by-frame basis,
331
850000
3000
上一帧一帧的基础上，
14:31
we could actually reconstruct a 3D head
332
853000
3000
其实，我们可以重建一个三维头部
14:34
that exactly matched the performance of Brad.
333
856000
3000
这正好符合了布拉德的表现。
14:37
So this was how the finished shot appeared in the film.
334
859000
3000
因此，这是如何拍摄完成的影片中出现。
14:40
And here you can see the body actor.
335
862000
2000
在这里你可以看到演员的身体。
14:42
And then this is what we called the "dead head," no reference to Jerry Garcia.
336
864000
3000
然后，这就是我们所谓的“死头”，不向杰里加西亚参考。
14:45
And then here's the reconstructed performance
337
867000
3000
然后这里的改造企业绩效
14:48
now with the timings of the performance.
338
870000
3000
现在的表现计时。
14:51
And then, again, the final shot.
339
873000
2000
然后，再次，最后一幕。
14:54
It was a long process.
340
876000
2000
这是一个漫长的过程。
14:56
(Applause)
341
878000
3000
（鼓掌）
15:07
The next section here, I'm going to just blast through this,
342
889000
2000
下一节在这里，我要通过这个刚刚爆炸，
15:09
because we could do a whole TEDTalk on the next several slides.
343
891000
4000
因为我们可以做多张幻灯片的下一个整体TEDTalk。
15:13
We had to create a lighting system.
344
895000
3000
我们必须创造一个照明系统。
15:16
So really, a big part of our processes was creating a lighting environment
345
898000
3000
因此，其实我们的很大一部分是在创造过程中的照明环境
15:19
for every single location that Benjamin had to appear
346
901000
2000
对于每一个位置，本杰明已经出现
15:21
so that we could put Ben's head into any scene
347
903000
3000
这样我们可以把任何场景本的头
15:24
and it would exactly match the lighting that's on the other actors
348
906000
3000
它会完全匹配的照明，关于其他方面的
15:27
in the real world.
349
909000
1000
在现实世界中。
15:28
We also had to create an eye system.
350
910000
3000
我们还必须建立一个眼系统。
15:31
We found the old adage, you know,
351
913000
2000
我们发现旧的格言，你知道，
15:33
"The eyes are the window to the soul,"
352
915000
2000
“眼睛是灵魂之，窗口”
15:35
absolutely true.
353
917000
1000
千真万确。
15:36
So the key here was to keep everybody looking in Ben's eyes.
354
918000
2000
因此，这里的关键是保持大家在Ben的眼睛。
15:38
And if you could feel the warmth, and feel the humanity,
355
920000
2000
如果你能感受到温暖，感受到人类，
15:40
and feel his intent coming through the eyes,
356
922000
3000
他的意图和感受来通过眼睛，
15:43
then we would succeed.
357
925000
1000
然后我们会成功。
15:44
So we had one person focused on the eye system
358
926000
3000
因此，我们有一个人对眼睛的聚焦系统
15:47
for almost two full years.
359
929000
2000
几乎整整两年。
15:49
We also had to create a mouth system.
360
931000
2000
我们还必须创建一个口系统。
15:51
We worked from dental molds of Brad.
361
933000
2000
我们还必须创建一个口系统。
15:53
We had to age the teeth over time.
362
935000
2000
我们必须随着时间的推移年龄的牙齿。
15:55
We also had to create an articulating tongue that allowed him to enunciate his words.
363
937000
3000
我们还必须创造一个阐明舌头，让他阐述他的话。
15:58
There was a whole system written in software to articulate the tongue.
364
940000
2000
整个系统有一个软件书面阐明了舌头。
16:00
We had one person devoted to the tongue for about nine months.
365
942000
2000
我们有一个人专门为约9个月的舌头。
16:02
He was very popular.
366
944000
2000
他很受欢迎。
16:04
Skin displacement: another big deal.
367
946000
3000
皮肤位移：另一个大问题。
16:07
The skin had to be absolutely accurate.
368
949000
2000
皮肤必须绝对准确，
16:09
He's also in an old age home, he's in a nursing home
369
951000
3000
而且他也有一老年之家，他在一家养老院
16:12
around other old people,
370
954000
2000
周围的其他老人，
16:14
so he had to look exactly the same as the others.
371
956000
2000
所以他看的人完全一样。
16:16
So, lots of work on skin deformation,
372
958000
1000
因此，大量的工作，对皮肤变形，
16:17
you can see in some of these cases it works,
373
959000
1000
你可以看到在这些情况下，一些作品，
16:18
in some cases it looks bad.
374
960000
1000
在某些情况下，它看起来不错，
16:19
This is a very, very, very early test in our process.
375
961000
2000
这是一个非常，非常，很早就在我们的测试过程。
16:21
So, effectively we created a digital puppet
376
963000
3000
所以，我们创建了一个有效的数字傀儡
16:24
that Brad Pitt could operate with his own face.
377
966000
3000
可经营的布拉德皮特与他自己的脸。
16:27
There were no animators necessary to come in and interpret behavior
378
969000
4000
有没有必要来在动画和解释行为
16:31
or enhance his performance.
379
973000
2000
或加强他的表现。
16:33
There was something that we encountered, though,
380
975000
3000
有些东西，我们遇到的，虽然，
16:36
that we ended up calling "the digital Botox effect."
381
978000
3000
这要求我们结束了“数字肉毒杆菌的效果。”
16:39
So, as things went through this process,
382
981000
3000
因此，在这个过程中经历的事情，
16:42
Fincher would always say, "It sandblasts the edges off of the performance."
383
984000
3000
芬奇总是说：“这sandblasts边关闭的表现。”
16:45
And thing our process and the technology couldn't do,
384
987000
3000
其中一件我们的工艺和技术不能做
16:48
is they couldn't understand intent,
385
990000
3000
它是无法理解的意图，
16:51
the intent of the actor.
386
993000
2000
该演员意图。
16:53
So it sees a smile as a smile.
387
995000
2000
因此，它认为，作为一个微笑的微笑。
16:55
It doesn't recognize an ironic smile, or a happy smile,
388
997000
3000
它不承认一个具有讽刺意味的微笑，或者一个幸福的微笑，
16:58
or a frustrated smile.
389
1000000
1000
或沮丧的笑容。
16:59
So it did take humans to kind of push it one way or another.
390
1001000
3000
因此，它确实需要人类推到一个或另一种方式。
17:02
But we ended up calling the entire process
391
1004000
3000
但我们最终调用的全过程
17:05
and all the technology "emotion capture,"
392
1007000
2000
和所有的技术“情感捕捉”
17:07
as opposed to just motion capture.
393
1009000
1000
而不仅仅是动作捕捉。
17:08
Take another look.
394
1010000
2000
再来看看。
17:11
Brad Pitt: Well, I heard momma and Tizzy whisper,
395
1013000
2000
布拉德皮特：嗯，我听到妈妈和如痴如醉的耳语，
17:13
and they said I was gonna die soon,
396
1015000
2000
他们说我是将要死去不久，
17:15
but ... maybe not.
397
1017000
2000
但是...也许不会。
17:37
EU: That's how to create a digital human in 18 minutes.
398
1039000
3000
埃德尔布里奇：这是如何创建一个数字人体在18分钟。
17:40
(Applause)
399
1042000
3000
（掌声）
17:48
A couple of quick factoids;
400
1050000
2000
一个快速改编过的夫妇。
17:50
it really took 155 people over two years,
401
1052000
4000
他花费了155人超过两年的时间，
17:54
and we didn't even talk about 60 hairstyles and an all-digital haircut.
402
1056000
4000
我们甚至没有谈到60发型和全数字理发。
17:58
But, that is Benjamin. Thank you.
403
1060000
3000
但是，这是本杰明。谢谢。
ABOUT THE SPEAKER
Ed Ulbrich - Visual storytellerEd Ulbrich works at the leading edge of computer-generated visuals. On a recent project, filmmakers, artists, and technologists have been working at a breakthrough point where reality and digitally created worlds collide.
Why you should listen
Ed Ulbrich spoke at TED2009 representing a team of filmmakers, artists and technologists who've been working on a significant breakthrough in visual storytelling -- a startling blurring of the line between digital creation and actor.
Ulbrich was the long time executive VP of production at Digital Domain, for whom he executive-produced Academy Award-winning visual effects for Titanic, What Dreams May Come, Fight Club, Zodiac, Adaptation and other features, as well as music videos and more than 500 commercials. He has recently exited this position but has entered into a creative consultant arrangement with the company. In 2007, he was named to the Creativity 50 -- top innovators in advertising and design.
Ed Ulbrich | Speaker | TED.com