that worked together on a remarkable film project for the last four years.

今天我代表一群藝術家、技術人員、電影製作團隊

And along the way they created a breakthrough in computer visualization.

過去四年間，我們共同完成了一項非凡的電影工程

So I want to show you a clip of the film now.

過程中也突破了電影繪圖技術

Hopefully it won't stutter.

我先讓大家看個電影片段

And if we did our jobs well, you won't know that we were even involved.

希望播放時不會卡住

Voice (Video): I don't know how it's possible ...

如果我們做好工作的話，你們不會看出我們動了什麼手腳

but you seem to have more hair.

影片: 我不知道這是怎麼回事

Brad Pitt: What if I told you that I wasn't getting older ...

但你頭髮好像變多了

but I was getting younger than everybody else?

班傑明巴頓: 如果我告訴你，我沒有越來越老

I was born with some form of disease.

反而是越來越年輕了呢?

Voice: What kind of disease?

我出生就有一種病

BP: I was born old.

什麼樣的病?

Man: I'm sorry.

我出生就是老人的樣子

BP: No need to be. There's nothing wrong with old age.

我很遺憾

Girl: Are you sick?

不用遺憾，老又沒有錯

BP: I heard momma and Tizzy whisper,

你生病了嗎?

and they said I was gonna die soon.

我聽到媽和Tizzy講悄悄話

But ... maybe not.

說我活不了多久

Girl: You're different than anybody I've ever met.

但... 也許他們說錯了

BB: There were many changes ...

我沒見過像你這樣的人

some you could see, some you couldn't.

我身體開始變化

Hair started growing in all sorts of places,

有些看的見，有些則不行

along with other things.

體毛開始到處長

I felt pretty good, considering.

還有一些其他東西

Ed Ulbrich: That was a clip from "The Curious Case of Benjamin Button."

其實這感覺還不賴

Many of you, maybe you've seen it or you've heard of the story,

Ed Ulbrich: 這是電影"班傑明的奇幻旅程"片段

but what you might not know

相信很多人已經看過、或聽過這故事

is that for nearly the first hour of the film,

但你也許不知道

the main character, Benjamin Button, who's played by Brad Pitt,

電影前將近一小時

is completely computer-generated from the neck up.

由布萊德彼特飾演的主角 班傑明巴頓

Now, there's no use of prosthetic makeup

頸部以上完全是電腦合成的

or photography of Brad superimposed over another actor's body.

沒有靠任何化妝技術

We've created a completely digital human head.

也不是布萊德的臉，蓋過另一個演員的身體

So I'd like to start with a little bit of history on the project.

我們全以數位方式製造出人頭

This is based on an F. Scott Fitzgerald short story.

我先稍微說一下製作起源

It's about a man who's born old and lives his life in reverse.

電影改編自史考特．費滋傑羅的短篇故事

Now, this movie has floated around Hollywood

關於一個出生時80歲的男人，越活越年輕的故事

for well over half a century,

這部電影在好萊塢就謠傳了很久

and we first got involved with the project in the early '90s,

超過50年有吧

with Ron Howard as the director.

我們第一次接觸這計劃是在1990年初

We took a lot of meetings and we seriously considered it.

導演是朗霍華

But at the time we had to throw in the towel.

我們討論了很久，認真考慮要接

It was deemed impossible.

到後來真的必須放棄的時候

It was beyond the technology of the day to depict a man aging backwards.

這已經被認為是不可能的任務

The human form, in particular the human head,

當時的科技無法刻畫出返老還童的樣子

has been considered the Holy Grail of our industry.

整個人，特別是頭的部份

The project came back to us about a decade later,

在我們這一行，稱作是聖杯傳奇

and this time with a director named David Fincher.

約十年後又有人提起這計畫

Now, Fincher is an interesting guy.

這次的導演是大衛芬奇

David is fearless of technology,

芬奇真的是怪咖一個

and he is absolutely tenacious.

一點都不怕技術上困難

And David won't take "no."

就是堅持一定要做

And David believed, like we do in the visual effects industry,

沒有人能拒絕他

that anything is possible

大衛、和我們做特效的持同樣看法

as long as you have enough time, resources and, of course, money.

沒有什麼是不可能的

And so David had an interesting take on the film,

只要有足夠的時間、資源，當然還有資金

and he threw a challenge at us.

大衛對這部電影有獨特的想法

He wanted the main character of the film to be played

丟給我們這項考驗

from the cradle to the grave by one actor.

他要這部電影的主角，從出生到死亡

It happened to be this guy.

都要是同一個人來演

We went through a process of elimination and a process of discovery

也就是這個人

with David, and we ruled out, of course, swapping actors.

我們經過了一連串淘汰、一連串新發現

That was one idea: that we would have different actors,

由於大衛堅持，我們排除使用不同演員的方法

and we would hand off from actor to actor.

本來是想利用不同演員

We even ruled out the idea of using makeup.

分別演出不同階段的人生

We realized that prosthetic makeup just wouldn't hold up,

我們也排除利用化妝

particularly in close-up.

因為用石膏來弄根本做不出來

And makeup is an additive process. You have to build the face up.

尤其是近拍的時候

And David wanted to carve deeply into Brad's face

況且也要先做出一張臉才能化

to bring the aging to this character.

大衛想要在布萊德彼特的臉上刻畫出皺紋

He needed to be a very sympathetic character.

來表現出這角色的年老樣貌

So we decided to cast a series of little people

他必須是個能讓人感同身受的角色

that would play the different bodies of Benjamin

所以我們決定選出一批小人物

at the different increments of his life

來演出班傑明在不同人生階段

and that we would in fact create a computer-generated version of Brad's head,

的各種身體樣貌

aged to appear as Benjamin,

然後我們利用電腦合成出布萊德的頭

and attach that to the body of the real actor.

弄出不同年紀的班傑明

Sounded great.

在接上其他演員的身體

Of course, this was the Holy Grail of our industry,

聽起來很可行

and the fact that this guy is a global icon didn't help either,

當然，這可是我們這行的聖杯傳奇

because I'm sure if any of you ever stand in line at the grocery store,

加上這傢伙沒有人不認識

you know -- we see his face constantly.

只要去過雜貨店一定看過他的臉

So there really was no tolerable margin of error.

這可不是什麼好處

There were two studios involved: Warner Brothers and Paramount.

正因如此我們不能出錯

And they both believed this would make an amazing film, of course,

過程中由兩個製片公司一起合作: 華納兄弟和派拉蒙

but it was a very high-risk proposition.

當然，他們都深信這會是一部很讚的電影

There was lots of money and reputations at stake.

無庸置疑也是很冒險的計劃

But we believed that we had a very solid methodology

攸關大把金錢與名聲

that might work ...

我們認為我們有很可靠的方法

But despite our verbal assurances,

有可能成功的

they wanted some proof.

但我們的口頭保證不夠

And so, in 2004, they commissioned us to do a screen test of Benjamin.

他們要看到證據

And we did it in about five weeks.

所以在2004年，他們要求看到班傑明的試鏡畫面

But we used lots of cheats and shortcuts.

我們做了約五週

We basically put something together to get through the meeting.

用了些旁門左道

I'll roll that for you now. This was the first test for Benjamin Button.

基本上我們東加西減地混過會談

And in here, you can see, that's a computer-generated head --

現在放給各位看。這是第一個班傑明巴頓

pretty good -- attached to the body of an actor.

在這裡可以看出是電腦合成出來的頭

And it worked. And it gave the studio great relief.

其實不錯，可以接到演員的身體

After many years of starts and stops on this project,

也算成功，製片那邊終於放下大石

and making that tough decision,

經過多年走走停停

they finally decided to greenlight the movie.

作出一些困難的決定

And I can remember, actually, when I got the phone call to congratulate us,

他們終於同意了

to say the movie was a go,

我還記得，當我接到電話

I actually threw up.

恭喜我們電影終於可以開拍

(Laughter)

我還吐了

You know, this is some tough stuff.

(笑聲)

So we started to have early team meetings,

這是艱難的工作

and we got everybody together,

我們開始初期的團隊會議

and it was really more like therapy in the beginning,

集合大家

convincing each other and reassuring each other that we could actually undertake this.

剛開始有點像在諮商治療

We had to hold up an hour of a movie with a character.

告訴彼此，我們一定做得到的

And it's not a special effects film; it has to be a man.

要能撐過電影一個小時

We really felt like we were in a -- kind of a 12-step program.

而這不是特效片，必須用真人

And of course, the first step is: admit you've got a problem. (Laughter)

這真的感覺像是戒酒那種12步計畫

So we had a big problem:

當然第一步就是: 承認問題的存在

we didn't know how we were going to do this.

我們問題可大了

But we did know one thing.

不曉得到底怎麼開始

Being from the visual effects industry,

但我們知道

we, with David, believed that we now had enough time,

作視覺特效這行

enough resources, and, God, we hoped we had enough money.

我們和大衛相信的，只有足夠時間

And we had enough passion to will the processes and technology into existence.

足夠資源，天啊，希望我們有足夠資金

So, when you're faced with something like that,

我們也有足夠的熱誠，成功的決心

of course you've got to break it down.

當你面對這樣的情況

You take the big problem and you break it down into smaller pieces

當然得先開始分析問題

and you start to attack that.

你面前有個大問題，把它拆成小問題

So we had three main areas that we had to focus on.

個個攻破

We needed to make Brad look a lot older --

主要集中在三個點

needed to age him 45 years or so.

我們要布萊德看起來很老

And we also needed to make sure that we could take Brad's idiosyncrasies,

我們要幫他加個45歲左右

his little tics, the little subtleties that make him who he is

我們得確定它有布萊德的臉部特徵

and have that translate through our process

臉部肌肉的抽動，各種他特有的細微變化

so that it appears in Benjamin on the screen.

經過我們的製作過程

And we also needed to create a character

讓班傑明能夠呈現於大螢幕

that could hold up under, really, all conditions.

我們也需要創造一個

He needed to be able to walk in broad daylight,

能夠做出每件事的角色

at nighttime, under candlelight,

他要能走在陽光下、

he had to hold an extreme close-up,

夜晚、燭光下

he had to deliver dialogue,

近拍不能露餡

he had to be able to run, he had to be able to sweat,

要能唸台詞

he had to be able to take a bath, to cry,

要能跑、能流汗

he even had to throw up.

能洗澡、能哭

Not all at the same time --

甚至要能嘔吐

but he had to, you know, do all of those things.

當然不是同時

And the work had to hold up for almost the first hour of the movie.

但他要能做到每件事

We did about 325 shots.

而且要能撐住電影前一小時

So we needed a system that would allow Benjamin

我們拍了325個景

to do everything a human being can do.

我們需要一個系統

And we realized that there was a giant chasm

讓班傑明做出人類能做的所有事

between the state of the art of technology in 2004

我們知道2004年當時最先進的技術

and where we needed it to be.

和我們所想要的技術

So we focused on motion capture.

仍有很大一段距離

I'm sure many of you have seen motion capture.

所以我們專注於動態捕捉技術

The state of the art at the time

我相信大部分的人都看過動態捕捉

was something called marker-based motion capture.

當時最先進的技術是

I'll give you an example here.

利用標記點的動態捕捉

It's basically the idea of, you wear a leotard,

給大家看個例子

and they put some reflective markers on your body,

主要就是，穿著緊身衣

and instead of using cameras,

在身上標出一些反光標記點

there're infrared sensors around a volume,

物體四周放置紅外線感應

and those infrared sensors track the three-dimensional position

而不是攝影機

of those markers in real time.

這些紅外線感應，會追蹤標記點

And then animators can take the data of the motion of those markers

當時的3D位置

and apply them to a computer-generated character.

接著動畫師把標記點的數據

You can see the computer characters on the right

輸入到電腦做出來的角色上

are having the same complex motion as the dancers.

可以看到右邊的動畫角色

But we also looked at numbers of other films at the time

也能做出和舞者一樣的複雜動作

that were using facial marker tracking,

我們也看了一些

and that's the idea of putting markers on the human face

使用臉部標記點的電影

and doing the same process.

就是把點標記在臉上

And as you can see, it gives you a pretty crappy performance.

過程相同

That's not terribly compelling.

可以看到，感覺蠻假的

And what we realized

這樣可沒法說服別人

was that what we needed

我們了解到

was the information that was going on between the markers.

我們所需要的

We needed the subtleties of the skin.

是點與點之間的數據

We needed to see skin moving over muscle moving over bone.

我們要皮膚的微妙變化

We needed creases and dimples and wrinkles and all of those things.

要能看到骨頭到肌肉到皮膚的變化

Our first revelation was to completely abort and walk away from

需要皺紋、酒窩、細紋等等

the technology of the day, the status quo, the state of the art.

我們了解現在需要完全放棄

So we aborted using motion capture.

當時最先進的技術

And we were now well out of our comfort zone,

我們放棄使用動態捕捉

and in uncharted territory.

丟下了自己所熟悉的技術

So we were left with this idea

到了陌生的領域

that we ended up calling "technology stew."

我們有了一種想法

We started to look out in other fields.

後來我們稱為科技大雜燴

The idea was that we were going to find

我們開始往別的領域找

nuggets or gems of technology

目的是要尋找出

that come from other industries like medical imaging,

其他科技領域像是醫學影像

the video game space,

或電玩空間技術

and re-appropriate them.

之中的稀世珍品

And we had to create kind of a sauce.

拿來重新研究

And the sauce was code in software

雜燴也需要點醬料

that we'd written to allow these disparate pieces of technology

就是軟體程式碼

to come together and work as one.

讓這些不同的領域的技術

Initially, we came across some remarkable research

能整合在一起

done by a gentleman named Dr. Paul Ekman in the early '70s.

起先，我們找到一項傑出的研究

He believed that he could, in fact,

是70年代初期，Paul Ekman博士提出的

catalog the human face.

他相信他有辦法

And he came up with this idea of Facial Action Coding System, or FACS.

將人臉目錄化

He believed that there were 70 basic poses

他想到使用臉部表情辨識系統(FACS)

or shapes of the human face,

他相信人的臉型

and that those basic poses or shapes of the face

有70種基本表情動作

can be combined to create infinite possibilities

只要把基本動作或臉型

of everything the human face is capable of doing.

結合起來就能創造出

And of course, these transcend age, race, culture, gender.

人臉做的出的無限表情

So this became the foundation of our research as we went forward.

不論年齡、種族、文化、性別，這70種動作都是一樣的

And then we came across some remarkable technology

這變成我們往後的基礎點

called Contour.

之後我們發現了項非凡的技術

And here you can see a subject having phosphorus makeup

叫做輪廓提取(Contour)

stippled on her face.

現在看到的，是在人臉上

And now what we're looking at is really creating a surface capture

輕輕塗上磷

as opposed to a marker capture.

接下來是表面捕捉

The subject stands in front of a computer array of cameras,

正好與點的捕捉相反

and those cameras can, frame-by-frame,

接著站在一排電腦攝影機前面

reconstruct the geometry of exactly what the subject's doing at the moment.

攝影機就會一景一景的

So, effectively, you get 3D data in real time of the subject.

重製出人當時的動作

And if you look in a comparison,

立刻就能得到3D數據

on the left, we see what volumetric data gives us

各位可以看看比較

and on the right you see what markers give us.

左邊是體積數據的結果

So, clearly, we were in a substantially better place for this.

右邊是標記點的

But these were the early days of this technology,

可以清楚看出，我們有很大的進步

and it wasn't really proven yet.

但這還是初期的結果

We measure complexity and fidelity of data

還沒完全成功