TED2009
Ed Ulbrich: How Benjamin Button got his face
Ed Ulbrih (Ed Ulbrich) pokazuje kako je Bendžamin Baton dobio svoje lice
Filmed:
Readability: 4.4
1,080,448 views
Ed Ulbrih, guru za digitalne efekte iz kompanije "Digital Domain", objašnjava tehnologiju koja je osvojila Oskara, a koja je omogućila njegovom timu da digitalno napravi mlađu i stariju verziju Bred Pitovog lica za film "Čudesni slučaj Bendžamina Batona".
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
Danas ovde predstavljam tim umetnika, tehničara i filmadžija, koji su
00:23
that worked together on a remarkable film project for the last four years.
1
5000
3000
zajedno radili na izuzetnom filmskom projektu u poslednje četiri godine.
00:26
And along the way they created a breakthrough in computer visualization.
2
8000
4000
Tokom tog rada, napravili su proboj u kompjuterskoj vizualizaciji.
00:30
So I want to show you a clip of the film now.
3
12000
3000
Sada želim da vam pokažem insert iz filma.
00:33
Hopefully it won't stutter.
4
15000
3000
Nadam se da neće zastajkivati.
00:36
And if we did our jobs well, you won't know that we were even involved.
5
18000
3000
I ako smo dobro uradili svoje poslove, nećete ni znati da smo bili prisutni.
00:39
Voice (Video): I don't know how it's possible ...
6
21000
3000
Glas (video): Ne znam da li je moguće --
00:42
but you seem to have more hair.
7
24000
3000
ali izgleda da imaš više kose.
00:45
Brad Pitt: What if I told you that I wasn't getting older ...
8
27000
3000
Bred Pit: Šta bi bilo kad bih ti rekao da ja ne starim...
00:48
but I was getting younger than everybody else?
9
30000
2000
nego postajem mlađi od svih ostalih?
00:53
I was born with some form of disease.
10
35000
3000
Rođen sam s nekom vrstom bolesti.
00:56
Voice: What kind of disease?
11
38000
2000
Glas: Kakvom vrstom bolesti?
00:58
BP: I was born old.
12
40000
2000
BP: Rođen sam star.
01:01
Man: I'm sorry.
13
43000
2000
Čovek: Žao mi je.
01:03
BP: No need to be. There's nothing wrong with old age.
14
45000
3000
BP: Nema potrebe. Nema ništa loše sa starošću.
01:08
Girl: Are you sick?
15
50000
2000
Devojčica: Da li si bolestan?
01:10
BP: I heard momma and Tizzy whisper,
16
52000
3000
BP: Čuo sam da mama i Tizi šapuću
01:13
and they said I was gonna die soon.
17
55000
2000
kako ću uskoro da umrem.
01:15
But ... maybe not.
18
57000
3000
Ali... možda i neću.
01:18
Girl: You're different than anybody I've ever met.
19
60000
3000
Devojčica: Ti si drugačiji od svih koje znam.
01:22
BB: There were many changes ...
20
64000
3000
BP: Bilo je mnogo promena...
01:25
some you could see, some you couldn't.
21
67000
3000
neke su bile primetne, druge ne.
01:28
Hair started growing in all sorts of places,
22
70000
3000
Dlake su počele da rastu na svakakvim mestima,
01:31
along with other things.
23
73000
3000
kao i neke druge stvari.
01:34
I felt pretty good, considering.
24
76000
3000
S obzirom na sve, osećao sam se prilično dobro.
01:38
Ed Ulbrich: That was a clip from "The Curious Case of Benjamin Button."
25
80000
4000
Ed Ulbrih: To je insert iz "Čudesnog slučaja Bendžamina Batona".
01:42
Many of you, maybe you've seen it or you've heard of the story,
26
84000
4000
Mnogi od vas su ga možda već videli ili čuli priču,
01:46
but what you might not know
27
88000
2000
ali ono što ne znate je da je,
01:48
is that for nearly the first hour of the film,
28
90000
2000
tokom skoro celog prvog sata filma,
01:50
the main character, Benjamin Button, who's played by Brad Pitt,
29
92000
3000
glavni junak, Bendžamin Baton, koga igra Bred Pit,
01:53
is completely computer-generated from the neck up.
30
95000
3000
u potpunosti kompjuterski generisan od vrata na gore.
01:56
Now, there's no use of prosthetic makeup
31
98000
3000
Scenska šminka nije bila od koristi,
01:59
or photography of Brad superimposed over another actor's body.
32
101000
3000
kao ni Bredova fotografija, montirana na telo drugog glumca.
02:02
We've created a completely digital human head.
33
104000
3000
Stvorili smo potpuno digitalnu ljudsku glavu.
02:05
So I'd like to start with a little bit of history on the project.
34
107000
3000
Počeću sa istorijskim podacima o projektu.
02:08
This is based on an F. Scott Fitzgerald short story.
35
110000
2000
Film je baziran na kratkoj priči F. Skota Ficdžeralda.
02:10
It's about a man who's born old and lives his life in reverse.
36
112000
3000
Radi se o čoveku koji je rođen star i živi život unazad.
02:13
Now, this movie has floated around Hollywood
37
115000
2000
Ovaj film je kružio Holivudom
02:15
for well over half a century,
38
117000
2000
više od pola veka,
02:17
and we first got involved with the project in the early '90s,
39
119000
3000
a mi smo se prvi put uključili ranih devedesetih,
02:20
with Ron Howard as the director.
40
122000
2000
kada je Ron Hauard bio režiser.
02:22
We took a lot of meetings and we seriously considered it.
41
124000
3000
Imali smo mnogo sastanaka i ozbiljno smo razmišljali o tome.
02:25
But at the time we had to throw in the towel.
42
127000
2000
Ali u to vreme smo morali da odustanemo.
02:27
It was deemed impossible.
43
129000
2000
Procenili smo da je nemoguće.
02:29
It was beyond the technology of the day to depict a man aging backwards.
44
131000
4000
Tehnologija tog vremena nije mogla da prikaže čovekovo starenje unazad.
02:33
The human form, in particular the human head,
45
135000
3000
Ljudski oblik, a naročito glava,
02:36
has been considered the Holy Grail of our industry.
46
138000
3000
smatrana je za Sveti Gral naše industrije.
02:39
The project came back to us about a decade later,
47
141000
3000
Oko deset godina kasnije projekat nam se vratio,
02:42
and this time with a director named David Fincher.
48
144000
3000
a ovog puta je režiser bio Dejvid Finčer.
02:45
Now, Fincher is an interesting guy.
49
147000
3000
Finčer je zanimljiv tip.
02:48
David is fearless of technology,
50
150000
2000
On se ne boji tehnologije,
02:50
and he is absolutely tenacious.
51
152000
2000
i vrlo je uporan.
02:52
And David won't take "no."
52
154000
2000
Ne prihvata "ne" kao odgovor.
02:54
And David believed, like we do in the visual effects industry,
53
156000
3000
Dejvid je, kao i mi u industriji vizuelnih efekata,
02:57
that anything is possible
54
159000
3000
verovao da je sve moguće, ako imate
03:00
as long as you have enough time, resources and, of course, money.
55
162000
3000
dovoljno vremena, resursa i naravno, novca.
03:03
And so David had an interesting take on the film,
56
165000
4000
Dejvid je imao zanimljiv pogled na film
03:07
and he threw a challenge at us.
57
169000
3000
i postavio nam je izazov.
03:10
He wanted the main character of the film to be played
58
172000
3000
Želeo je da glavnog lika u filmu, od kolevke
03:13
from the cradle to the grave by one actor.
59
175000
2000
do groba, igra jedan glumac.
03:15
It happened to be this guy.
60
177000
2000
Desilo se da je to ovaj momak.
03:17
We went through a process of elimination and a process of discovery
61
179000
3000
Sa Dejvidom smo prošli procese eliminacije i otkrivanja
03:20
with David, and we ruled out, of course, swapping actors.
62
182000
3000
i naravno, odbacili smo ideju zamene glumaca.
03:23
That was one idea: that we would have different actors,
63
185000
3000
To je bila jedna ideja: mogli smo imati različite glumce,
03:26
and we would hand off from actor to actor.
64
188000
2000
i snimali bismo naizmenično.
03:28
We even ruled out the idea of using makeup.
65
190000
2000
Čak smo odbacili ideju o korišćenju šminke.
03:30
We realized that prosthetic makeup just wouldn't hold up,
66
192000
3000
Shvatili smo da scenska šminka neće uspeti,
03:33
particularly in close-up.
67
195000
2000
naročito u krupnim kadrovima.
03:35
And makeup is an additive process. You have to build the face up.
68
197000
3000
Šminka je slojevit proces. Morate da izgradite lice.
03:38
And David wanted to carve deeply into Brad's face
69
200000
3000
A Dejvid je želeo da duboko ureže u Bredovo lice,
03:41
to bring the aging to this character.
70
203000
2000
da bi njegov lik ostario.
03:43
He needed to be a very sympathetic character.
71
205000
2000
Morao je da bude i vrlo simpatičan karakter.
03:45
So we decided to cast a series of little people
72
207000
3000
Zato smo odlučili da odaberemo nekoliko niskih ljudi
03:48
that would play the different bodies of Benjamin
73
210000
3000
koji bi igrali različita Bendžaminova tela,
03:51
at the different increments of his life
74
213000
2000
u različitim fazama njegovog života,
03:53
and that we would in fact create a computer-generated version of Brad's head,
75
215000
3000
a da kompjuterski napravimo verziju Bredove glave
03:56
aged to appear as Benjamin,
76
218000
2000
da po godinama podseća na Bendžamina,
03:58
and attach that to the body of the real actor.
77
220000
3000
i "povežemo" je na telo pravog glumca.
04:01
Sounded great.
78
223000
2000
Zvučalo je super.
04:03
Of course, this was the Holy Grail of our industry,
79
225000
3000
Naravno, to je bio Sveti Gral naše industrije,
04:06
and the fact that this guy is a global icon didn't help either,
80
228000
3000
a nije pomagala ni činjenica da je ovaj momak globalna ikona,
04:09
because I'm sure if any of you ever stand in line at the grocery store,
81
231000
3000
jer sam siguran da ako nekad stojite u redu u prodavnici
04:12
you know -- we see his face constantly.
82
234000
3000
-- njegovo lice stalno viđamo.
04:15
So there really was no tolerable margin of error.
83
237000
2000
Dakle, uopšte nije bilo mesta za grešku.
04:17
There were two studios involved: Warner Brothers and Paramount.
84
239000
3000
Učestvovala su dva studija: "Warner Brothers" i "Paramount".
04:20
And they both believed this would make an amazing film, of course,
85
242000
3000
Naravno, oba su verovala da će ovo biti izuzetan film,
04:23
but it was a very high-risk proposition.
86
245000
3000
ali to je bio posao visokog rizika.
04:26
There was lots of money and reputations at stake.
87
248000
3000
Mnogo je novca i reputacija bilo na kocki.
04:29
But we believed that we had a very solid methodology
88
251000
3000
Ali mi smo verovali da imamo jako dobru metodologiju
04:32
that might work ...
89
254000
3000
koja bi mogla da uspe...
04:35
But despite our verbal assurances,
90
257000
3000
Ali i pored naših verbalnih uveravanja,
04:38
they wanted some proof.
91
260000
2000
oni su hteli neke dokaze.
04:40
And so, in 2004, they commissioned us to do a screen test of Benjamin.
92
262000
3000
Tako su 2004. tražili od nas da uradimo probnu ekranizaciju Bendžamina.
04:43
And we did it in about five weeks.
93
265000
3000
Uradili smo je za otprilike pet nedelja.
04:46
But we used lots of cheats and shortcuts.
94
268000
3000
Ali dosta smo varali i koristili prečice.
04:49
We basically put something together to get through the meeting.
95
271000
3000
U stvari, samo smo nešto sklepali kako bismo prošli sastanak.
04:52
I'll roll that for you now. This was the first test for Benjamin Button.
96
274000
3000
Sad ću vam to pustiti. Ovo je prvi test Bendžamina Batona.
04:55
And in here, you can see, that's a computer-generated head --
97
277000
3000
Ovde možete videti da je to kompjuterski generisana glava -
04:58
pretty good -- attached to the body of an actor.
98
280000
3000
prilično dobra - montirana na telo nekog glumca.
05:01
And it worked. And it gave the studio great relief.
99
283000
3000
I uspelo je. Studiju je bilo mnogo lakše.
05:04
After many years of starts and stops on this project,
100
286000
3000
Posle dugogodišnjih započinjanja i pauza,
05:07
and making that tough decision,
101
289000
3000
i donošenja teških odluka o ovom projektu,
05:10
they finally decided to greenlight the movie.
102
292000
3000
konačno su odlučili da filmu daju zeleno svetlo.
05:13
And I can remember, actually, when I got the phone call to congratulate us,
103
295000
3000
Zapravo, sećam se telefonskog razgovora u kom su nam čestitali,
05:16
to say the movie was a go,
104
298000
2000
kad su rekli da će se snimati,
05:18
I actually threw up.
105
300000
2000
povratio sam.
05:20
(Laughter)
106
302000
2000
(smeh)
05:22
You know, this is some tough stuff.
107
304000
2000
Znate, ovo je vrlo ozbiljan posao.
05:24
So we started to have early team meetings,
108
306000
3000
Počeli smo sa ranim sastancima tima,
05:27
and we got everybody together,
109
309000
2000
okupili smo sve ljude,
05:29
and it was really more like therapy in the beginning,
110
311000
3000
na početku je to bilo više kao terapija,
05:32
convincing each other and reassuring each other that we could actually undertake this.
111
314000
3000
ubeđivali smo i uveravali jedni druge da možemo ovo da izvedemo.
05:35
We had to hold up an hour of a movie with a character.
112
317000
3000
Trebalo je da stvorimo sat vremena filma sa nekim likom.
05:38
And it's not a special effects film; it has to be a man.
113
320000
3000
To nije film sa specijalnim efektima; mora da bude čovek.
05:41
We really felt like we were in a -- kind of a 12-step program.
114
323000
3000
Stvarno smo se osećali kao da smo u nekom programu od 12 koraka.
05:44
And of course, the first step is: admit you've got a problem. (Laughter)
115
326000
3000
Naravno, prvi korak je: priznaj da imaš problem. (smeh)
05:48
So we had a big problem:
116
330000
2000
Imali smo veliki problem:
05:50
we didn't know how we were going to do this.
117
332000
3000
nismo znali kako ćemo ovo da uradimo.
05:53
But we did know one thing.
118
335000
2000
Ali znali smo jednu stvar:
05:55
Being from the visual effects industry,
119
337000
3000
pošto potičemo iz industrije vizuelnih efekata,
05:58
we, with David, believed that we now had enough time,
120
340000
3000
i mi i Dejvid smo mislili da imamo dovoljno vremena,
06:01
enough resources, and, God, we hoped we had enough money.
121
343000
3000
resursa i Bože, nadali smo se da imamo dovoljno novca.
06:04
And we had enough passion to will the processes and technology into existence.
122
346000
5000
A imali smo i dovoljno strasti da oživimo procese i tehnologiju.
06:09
So, when you're faced with something like that,
123
351000
2000
Kada ste suočeni sa nečim takvim,
06:11
of course you've got to break it down.
124
353000
2000
naravno da morate da ga razložite na delove.
06:13
You take the big problem and you break it down into smaller pieces
125
355000
2000
Uzmete veliki problem i raščlanite ga na manje delove
06:15
and you start to attack that.
126
357000
1000
i počnete njih da napadate.
06:16
So we had three main areas that we had to focus on.
127
358000
2000
Imali smo tri glavne celine na koje je trebalo da se fokusiramo.
06:18
We needed to make Brad look a lot older --
128
360000
2000
Da učinimo da Bred izgleda mnogo starije -
06:20
needed to age him 45 years or so.
129
362000
2000
da ostari oko 45 godina.
06:22
And we also needed to make sure that we could take Brad's idiosyncrasies,
130
364000
6000
I trebalo je da budemo sigurni da ćemo uhvatiti njegove specifičnosti,
06:28
his little tics, the little subtleties that make him who he is
131
370000
2000
njegove male tikove, nijanse koje ga čine onim ko je,
06:30
and have that translate through our process
132
372000
2000
i preneti ih kroz naš proces
06:32
so that it appears in Benjamin on the screen.
133
374000
3000
da bi se na ekranu pojavile u Bendžaminu.
06:35
And we also needed to create a character
134
377000
2000
I trebalo je da napravimo lik
06:37
that could hold up under, really, all conditions.
135
379000
3000
koji bi izdržao stvarno sve uslove.
06:40
He needed to be able to walk in broad daylight,
136
382000
2000
Da može da hoda usred bela dana,
06:42
at nighttime, under candlelight,
137
384000
3000
noću, pod svetlošću sveće,
06:45
he had to hold an extreme close-up,
138
387000
2000
morao je da bude u izuzetno krupnom planu,
06:47
he had to deliver dialogue,
139
389000
1000
da učestvuje u razgovoru,
06:48
he had to be able to run, he had to be able to sweat,
140
390000
2000
da može da trči, da se znoji,
06:50
he had to be able to take a bath, to cry,
141
392000
2000
da se kupa, da plače,
06:52
he even had to throw up.
142
394000
1000
čak je trebalo da povraća.
06:53
Not all at the same time --
143
395000
1000
Ne sve u isto vreme -
06:54
but he had to, you know, do all of those things.
144
396000
2000
ali je trebalo da radi sve te stvari.
06:56
And the work had to hold up for almost the first hour of the movie.
145
398000
3000
Taj rad je morao da izdrži skoro tokom prvog sata filma.
06:59
We did about 325 shots.
146
401000
2000
Uradili smo oko 325 snimaka.
07:01
So we needed a system that would allow Benjamin
147
403000
3000
Bio nam je potreban sistem koji bi omogućio Bendžaminu
07:04
to do everything a human being can do.
148
406000
3000
da radi sve što ljudsko biće može da radi.
07:07
And we realized that there was a giant chasm
149
409000
3000
Shvatili smo da postoji ogroman jaz
07:10
between the state of the art of technology in 2004
150
412000
3000
između toga gde se tehnologija nalazila 2004. godine
07:13
and where we needed it to be.
151
415000
2000
i onoga gde je trebalo da bude za naše potrebe.
07:15
So we focused on motion capture.
152
417000
3000
Fokusirali smo se na snimanje pokreta.
07:18
I'm sure many of you have seen motion capture.
153
420000
2000
Siguran sam da su mnogi od vas to videli.
07:20
The state of the art at the time
154
422000
2000
U to vreme je vrhunska umetnost bila
07:22
was something called marker-based motion capture.
155
424000
2000
nešto što se zove snimanje pokreta na osnovu markera.
07:24
I'll give you an example here.
156
426000
1000
Daću vam jedan primer.
07:25
It's basically the idea of, you wear a leotard,
157
427000
2000
Ideja je da nosite triko, a na vaše
07:27
and they put some reflective markers on your body,
158
429000
2000
telo se postave reflektujući označivači - markeri
07:29
and instead of using cameras,
159
431000
2000
i umesto da se koriste kamere,
07:31
there're infrared sensors around a volume,
160
433000
2000
tu su infracrveni senzori koji
07:33
and those infrared sensors track the three-dimensional position
161
435000
2000
u realnom vremenu prate trodimenzionalnu
07:35
of those markers in real time.
162
437000
2000
poziciju tih markera.
07:37
And then animators can take the data of the motion of those markers
163
439000
3000
Potom animatori mogu uzeti podatke o kretanju iz tih
07:40
and apply them to a computer-generated character.
164
442000
2000
markera i primeniti ih na kompjuterski generisan lik.
07:42
You can see the computer characters on the right
165
444000
3000
Vidite da kompjuterski generisani likovi s desne strane
07:45
are having the same complex motion as the dancers.
166
447000
3000
izvode iste složene pokrete kao i plesači.
07:48
But we also looked at numbers of other films at the time
167
450000
2000
Takođe smo gledali i veliki broj drugih filmova
07:50
that were using facial marker tracking,
168
452000
2000
koji su tada koristili praćenje pokreta lica,
07:52
and that's the idea of putting markers on the human face
169
454000
2000
a to je ideja da se označivači stave na lice
07:54
and doing the same process.
170
456000
1000
i obavi se isti proces.
07:55
And as you can see, it gives you a pretty crappy performance.
171
457000
4000
Kao što vidite, dobijate prilično jadan rezultat.
07:59
That's not terribly compelling.
172
461000
3000
To nije baš ubedljivo.
08:02
And what we realized
173
464000
2000
Shvatili smo
08:04
was that what we needed
174
466000
1000
da su nam potrebne
08:05
was the information that was going on between the markers.
175
467000
2000
informacije o dešavanjima između markera.
08:07
We needed the subtleties of the skin.
176
469000
3000
Potrebni su nam detalji kože.
08:10
We needed to see skin moving over muscle moving over bone.
177
472000
3000
Trebalo je da vidimo pokrete kože preko mišića i kostiju.
08:13
We needed creases and dimples and wrinkles and all of those things.
178
475000
2000
Trebale su nam linije, rupice, bore, sve te stvari.
08:15
Our first revelation was to completely abort and walk away from
179
477000
3000
Naše prvo otkrovenje bilo je da u potpunosti odustanemo
08:18
the technology of the day, the status quo, the state of the art.
180
480000
3000
od tadašnje tehnologije, statusa kvo, vrhunske umetnosti.
08:21
So we aborted using motion capture.
181
483000
3000
Odustali smo od korišćenja snimanja pokreta.
08:24
And we were now well out of our comfort zone,
182
486000
3000
Sada smo već bili prilično izvan zone udobnosti,
08:27
and in uncharted territory.
183
489000
2000
na neobeleženoj teritoriji.
08:29
So we were left with this idea
184
491000
3000
Ostali smo sa idejom koju smo
08:32
that we ended up calling "technology stew."
185
494000
3000
na kraju zvali "tehnološki paprikaš".
08:35
We started to look out in other fields.
186
497000
2000
Počeli smo da istražujemo u drugim poljima.
08:37
The idea was that we were going to find
187
499000
3000
Ideja je bila da pronađemo
08:40
nuggets or gems of technology
188
502000
2000
komadiće, dragulje tehnologije
08:42
that come from other industries like medical imaging,
189
504000
2000
koji dolaze iz drugih industrija kao što su
08:44
the video game space,
190
506000
1000
medicina ili video igre
08:45
and re-appropriate them.
191
507000
2000
i da ih prilagodimo.
08:47
And we had to create kind of a sauce.
192
509000
3000
Trebalo je da napravimo neku vrstu sosa.
08:50
And the sauce was code in software
193
512000
3000
A sos je bio kod u softveru, koji smo napisali
08:53
that we'd written to allow these disparate pieces of technology
194
515000
3000
kako bismo omogućili da se ovi različiti delovi tehnologije
08:56
to come together and work as one.
195
518000
2000
spoje i funkcionišu kao jedan.
08:58
Initially, we came across some remarkable research
196
520000
2000
Prvo smo naišli na izuzetno istraživanje
09:00
done by a gentleman named Dr. Paul Ekman in the early '70s.
197
522000
3000
koje je sproveo gospodin po imenu dr Pol Ekman, ranih '70-ih.
09:03
He believed that he could, in fact,
198
525000
3000
On je verovao da može
09:06
catalog the human face.
199
528000
2000
da katalogizuje ljudsko lice.
09:08
And he came up with this idea of Facial Action Coding System, or FACS.
200
530000
3000
Osmislio je Sistem kodiranja facijalne akcije, SKFA.
09:11
He believed that there were 70 basic poses
201
533000
3000
Smatrao je da postoji sedamdeset osnovnih poza
09:14
or shapes of the human face,
202
536000
3000
ili oblika ljudskog lica,
09:17
and that those basic poses or shapes of the face
203
539000
3000
i da te osnovne poze ili oblici
09:20
can be combined to create infinite possibilities
204
542000
3000
mogu da se kombinuju i stvore nebrojene mogućnosti
09:23
of everything the human face is capable of doing.
205
545000
2000
svega što je ljudsko lice sposobno da uradi.
09:25
And of course, these transcend age, race, culture, gender.
206
547000
3000
Naravno, oni su nezavisni od godina, rase, kulture, pola.
09:28
So this became the foundation of our research as we went forward.
207
550000
4000
Kako smo napredovali, to je postala osnova našeg istraživanja.
09:32
And then we came across some remarkable technology
208
554000
3000
Onda smo naišli na jednu izuzetnu tehnologiju
09:35
called Contour.
209
557000
1000
po imenu "Kontura".
09:36
And here you can see a subject having phosphorus makeup
210
558000
3000
Ovde vidite da subjekt ima fosfornu šminku
09:39
stippled on her face.
211
561000
2000
nanesenu na lice.
09:41
And now what we're looking at is really creating a surface capture
212
563000
3000
Sada zapravo možemo da snimimo povšinu,
09:44
as opposed to a marker capture.
213
566000
2000
umesto snimanja samo označivača.
09:46
The subject stands in front of a computer array of cameras,
214
568000
2000
Ovaj subjekt stoji ispred kompjuterskih kamera
09:48
and those cameras can, frame-by-frame,
215
570000
2000
i one mogu, kadar po kadar, da rekonstruišu
09:50
reconstruct the geometry of exactly what the subject's doing at the moment.
216
572000
3000
geometriju upravo onoga što subjekt radi u trenutku.
09:53
So, effectively, you get 3D data in real time of the subject.
217
575000
5000
Bukvalno dobijate 3D podatke o subjektu u realnom vremenu.
09:58
And if you look in a comparison,
218
580000
3000
Ako pogledamo uporedo,
10:01
on the left, we see what volumetric data gives us
219
583000
3000
levo vidimo šta nam podaci o zapremini daju,
10:04
and on the right you see what markers give us.
220
586000
2000
a desno vidimo šta nam označivači daju.
10:07
So, clearly, we were in a substantially better place for this.
221
589000
2000
Jasno je da smo bili u mnogo boljem položaju za ovo.
10:09
But these were the early days of this technology,
222
591000
2000
Ali to su bili rani dani te tehnologije
10:11
and it wasn't really proven yet.
223
593000
2000
i još nije bila dokazana.
10:13
We measure complexity and fidelity of data
224
595000
2000
Merimo složenost i preciznost podataka
10:15
in terms of polygonal count.
225
597000
2000
u smislu broja poligona.
10:17
And so, on the left, we were seeing 100,000 polygons.
226
599000
3000
Tako, s leve strane imamo 100 000 poligona.
10:20
We could go up into the millions of polygons.
227
602000
2000
Mogli bismo da dostignemo milione poligona.
10:22
It seemed to be infinite.
228
604000
2000
Izgledalo je neograničeno.
10:24
This was when we had our "Aha!"
229
606000
2000
Tada smo doživeli "Aha!" trenutak.
10:26
This was the breakthrough.
230
608000
1000
To je bio proboj.
10:27
This is when we're like, "OK, we're going to be OK,
231
609000
2000
Tada smo pomislili, "OK, bićemo dobro.
10:29
This is actually going to work."
232
611000
1000
Ovo će zaista uspeti."
10:30
And the "Aha!" was, what if we could take Brad Pitt,
233
612000
4000
A "Aha!" je bilo: šta ako bismo uzeli Breda
10:34
and we could put Brad in this device,
234
616000
3000
i stavili ga u ovu spravu
10:37
and use this Contour process,
235
619000
2000
i iskoristili "Kontura" proces
10:39
and we could stipple on this phosphorescent makeup
236
621000
2000
i naneli mu fluorescentnu šminku
10:41
and put him under the black lights,
237
623000
1000
i stavili ga pod "blacklight"
10:42
and we could, in fact, scan him in real time
238
624000
3000
- mogli bismo da ga skeniramo u realnom vremenu
10:45
performing Ekman's FACS poses.
239
627000
2000
koristeći Ekmanove SKFA poze.
10:47
Right? So, effectively,
240
629000
2000
Je l' tako? Dakle, bukvalno
10:49
we ended up with a 3D database
241
631000
2000
smo dobili 3D bazu podataka
10:51
of everything Brad Pitt's face is capable of doing.
242
633000
3000
svih pokreta koje je lice Breda Pita u stanju da uradi.
10:54
(Laughter)
243
636000
2000
(smeh)
10:56
From there, we actually carved up those faces
244
638000
3000
Odatle smo isekli ta lica
10:59
into smaller pieces and components of his face.
245
641000
3000
na manje delove i komponente njegovog lica.
11:02
So we ended up with literally thousands and thousands and thousands of shapes,
246
644000
3000
Dobili smo bukvalno hiljade i hiljade i hiljade oblika,
11:05
a complete database of all possibilities
247
647000
3000
kompletnu bazu podataka svih mogućnosti
11:08
that his face is capable of doing.
248
650000
3000
koje ovo lice može da izvede.
11:11
Now, that's great, except we had him at age 44.
249
653000
3000
To je super, ali mi smo ga snimili sa 44 godine.
11:14
We need to put another 40 years on him at this point.
250
656000
3000
Tada je trebalo da mu dodamo još 40 godina.
11:17
We brought in Rick Baker,
251
659000
2000
Doveli smo Rika Bejkera, koji je
11:19
and Rick is one of the great makeup and special effects gurus
252
661000
2000
jedan od odličnih gurua za šminku i specijalne efekte
11:21
of our industry.
253
663000
1000
u našoj industriji.
11:22
And we also brought in a gentleman named Kazu Tsuji,
254
664000
3000
Doveli smo i gospodina po imenu Kazu Tsudži,
11:25
and Kazu Tsuji is one of the great photorealist sculptors of our time.
255
667000
3000
a on je jedan od najboljih fotorealističnih skulptora našeg vremena.
11:28
And we commissioned them to make a maquette,
256
670000
3000
Tražili smo od njih da naprave maketu,
11:31
or a bust, of Benjamin.
257
673000
2000
bistu Bendžamina.
11:33
So, in the spirit of "The Great Unveiling" -- I had to do this --
258
675000
3000
U duhu "Velikog otkrivanja" - morao sam ovo da uradim -
11:36
I had to unveil something.
259
678000
2000
morao sam nešto da otkrijem.
11:38
So this is Ben 80.
260
680000
2000
Ovo je Ben 80.
11:40
We created three of these:
261
682000
2000
Napravili smo tri ovakva:
11:42
there's Ben 80, there's Ben 70, there's Ben 60.
262
684000
2000
imamo Bena 80, Bena 70, Bena 60.
11:44
And this really became the template for moving forward.
263
686000
3000
Ovo je postao šablon za napredovanje.
11:47
Now, this was made from a life cast of Brad.
264
689000
2000
Ovo je napravljeno od pravog odlivka Breda.
11:49
So, in fact, anatomically, it is correct.
265
691000
3000
Dakle, anatomski je tačno.
11:52
The eyes, the jaw, the teeth:
266
694000
3000
Oči, vilica, zubi:
11:55
everything is in perfect alignment with what the real guy has.
267
697000
3000
sve se savršeno poklapa sa pravim čovekom.
11:58
We have these maquettes scanned into the computer
268
700000
2000
Skenirali smo ove makete
12:00
at very high resolution --
269
702000
2000
sa veoma visokom rezolucijom -
12:02
enormous polygonal count.
270
704000
2000
imaju ogroman broj poligona.
12:04
And so now we had three age increments of Benjamin
271
706000
4000
Sada smo u kompjuteru imali Bendžamina
12:08
in the computer.
272
710000
2000
u tri starosne verzije.
12:10
But we needed to get a database of him doing more than that.
273
712000
3000
Ali bila nam je potrebna baza sa više pokreta.
12:13
We went through this process, then, called retargeting.
274
715000
3000
Prošli smo kroz proces koji se zove ponovno mapiranje.
12:16
This is Brad doing one of the Ekman FACS poses.
275
718000
2000
Ovde Bred izvodi jednu od Ekmanovih SKFA poza.
12:18
And here's the resulting data that comes from that,
276
720000
3000
A evo podataka koji su rezultat toga,
12:21
the model that comes from that.
277
723000
2000
model koji iz toga nastaje.
12:23
Retargeting is the process of transposing that data
278
725000
3000
Ponovno mapiranje je proces prenošenja
12:26
onto another model.
279
728000
2000
tih podataka na drugi model.
12:28
And because the life cast, or the bust -- the maquette -- of Benjamin
280
730000
3000
Budući da je model Bendžamina - bista ili maketa -
12:31
was made from Brad,
281
733000
2000
napravljena od Breda,
12:33
we could transpose the data of Brad at 44
282
735000
3000
mogli smo da prenesemo podatke Breda sa
12:36
onto Brad at 87.
283
738000
2000
44 godine, na onog sa 87.
12:38
So now, we had a 3D database of everything Brad Pitt's face can do
284
740000
3000
Sada smo imali bazu svega što Bredovo lice može da uradi
12:41
at age 87, in his 70s and in his 60s.
285
743000
4000
u 87. godini, u sedamdesetim i šezdesetim.
12:45
Next we had to go into the shooting process.
286
747000
3000
Potom je trebalo da pređemo na snimanje.
12:48
So while all that's going on,
287
750000
1000
Dok se sve to dešava,
12:49
we're down in New Orleans and locations around the world.
288
751000
2000
mi se nalazimo u Nju Orleansu i lokacijama širom sveta.
12:51
And we shot our body actors,
289
753000
2000
Snimali smo tela drugih glumaca
12:53
and we shot them wearing blue hoods.
290
755000
2000
dok su nosili plave kapuljače.
12:55
So these are the gentleman who played Benjamin.
291
757000
2000
Ovo su sve gospoda koja su igrala Bendžamina.
12:57
And the blue hoods helped us with two things:
292
759000
2000
Plave kapuljače su nam pomogle na dva načina:
12:59
one, we could easily erase their heads;
293
761000
2000
Prvo, tako smo lako mogli da izbrišemo njihove glave;
13:01
and we also put tracking markers on their heads
294
763000
2000
a takođe smo im stavili markere pokreta na glave,
13:03
so we could recreate the camera motion
295
765000
2000
kako bismo ponovili pokrete kamere
13:05
and the lens optics from the set.
296
767000
2000
i optiku sa snimanja.
13:07
But now we needed to get Brad's performance to drive our virtual Benjamin.
297
769000
3000
Zatim je Bredovo izvođenje trebalo da pokreće virtualnog Bendžamina.
13:10
And so we edited the footage that was shot on location
298
772000
2000
Montirali smo snimke sa lokacija
13:12
with the rest of the cast and the body actors
299
774000
3000
sa ostatkom ekipe i glumcima-telima
13:15
and about six months later
300
777000
2000
i oko šest meseci kasnije
13:17
we brought Brad onto a sound stage in Los Angeles
301
779000
3000
doveli smo Breda u zvučni studio u Los Anđelesu
13:20
and he watched on the screen.
302
782000
3000
i on je gledao na ekranu.
13:23
His job, then, was to become Benjamin.
303
785000
2000
Njegov posao je onda bio da postane Bendžamin.
13:25
And so we looped the scenes.
304
787000
1000
Ponavljali smo scene.
13:26
He watched again and again.
305
788000
1000
Gledao je iznova i iznova.
13:27
We encouraged him to improvise.
306
789000
2000
Podsticali smo ga da improvizuje.
13:29
And he took Benjamin into interesting and unusual places
307
791000
3000
Odveo je Bendžamina na zanimljiva i neobična mesta
13:32
that we didn't think he was going to go.
308
794000
2000
na koja nismo mislili da će ga povesti.
13:34
We shot him with four HD cameras
309
796000
2000
Snimali smo ga sa 4 kamere visoke rezolucije
13:36
so we'd get multiple views of him
310
798000
1000
kako bismo imali više uglova
13:37
and then David would choose the take of Brad being Benjamin
311
799000
3000
a onda bi Dejvid odabrao snimak Breda kao Bendžamina
13:40
that he thought best matched the footage
312
802000
3000
za koji je mislio da se najbolje
13:43
with the rest of the cast.
313
805000
1000
uklapa sa ostalim glumcima.
13:44
From there we went into a process called image analysis.
314
806000
3000
Odatle smo prešli u proces analize snimka.
13:47
And so here, you can see again, the chosen take.
315
809000
3000
Ovde opet vidite izabrani snimak.
13:50
And you are seeing, now, that data being transposed on to Ben 87.
316
812000
3000
Ovde vidite kako se on prenosi na Bena sa 87 godina.
13:53
And so, what's interesting about this is
317
815000
3000
Zanimljivo je ovde da smo
13:56
we used something called image analysis,
318
818000
2000
koristili analizu snimka, koja
13:58
which is taking timings from different components of Benjamin's face.
319
820000
3000
uzima vremenske tačke različitih komponenti Bendžaminovog lica.
14:01
And so we could choose, say, his left eyebrow.
320
823000
3000
Mogli smo, recimo, da odaberemo njegovu levu obrvu.
14:04
And the software would tell us that, well,
321
826000
2000
A softver bi nam rekao kako
14:06
in frame 14 the left eyebrow begins to move from here to here,
322
828000
2000
u 14. slici leva obrva počinje da se kreće
14:08
and it concludes moving in frame 32.
323
830000
2000
i kako završava pokret u 32. slici.
14:10
And so we could choose numbers of positions on the face
324
832000
2000
Mogli smo da izaberemo broj pozicija na licu
14:12
to pull that data from.
325
834000
2000
iz kojih smo uzimali podatke.
14:14
And then, the sauce I talked about with our technology stew --
326
836000
2000
A onda, sos o kom sam govorio u našem tehnološkom paprikašu -
14:16
that secret sauce was, effectively, software that allowed us to
327
838000
3000
tajni sos je bio, bukvalno, softver koji je omogućio
14:19
match the performance footage of Brad
328
841000
3000
da povežemo snimak Bredovog izvođenja
14:22
in live action with our database of aged Benjamin,
329
844000
4000
uživo, sa bazom podataka starog Bendžamina,
14:26
the FACS shapes that we had.
330
848000
2000
SKFA pozama koje smo imali.
14:28
On a frame-by-frame basis,
331
850000
3000
Na nivou jedne-po-jedne slike,
14:31
we could actually reconstruct a 3D head
332
853000
3000
mogli smo da rekonstruišemo 3D glavu
14:34
that exactly matched the performance of Brad.
333
856000
3000
koja se potpuno poklapala sa Bredovim izvođenjem.
14:37
So this was how the finished shot appeared in the film.
334
859000
3000
Ovako je završeni snimak izgledao na filmu.
14:40
And here you can see the body actor.
335
862000
2000
Možete videti glumca za telo.
14:42
And then this is what we called the "dead head," no reference to Jerry Garcia.
336
864000
3000
Ovo smo zvali "mrtva glava", što nema veze sa Džerijem Garsijom.
14:45
And then here's the reconstructed performance
337
867000
3000
A evo i rekonstruisanog izvođenja
14:48
now with the timings of the performance.
338
870000
3000
zajedno sa vremenskim zapisom izvođenja.
14:51
And then, again, the final shot.
339
873000
2000
I ponovo, konačni snimak.
14:54
It was a long process.
340
876000
2000
Bio je to dug proces.
14:56
(Applause)
341
878000
3000
(aplauz)
15:07
The next section here, I'm going to just blast through this,
342
889000
2000
Brzo ću proći kroz sledeći deo jer
15:09
because we could do a whole TEDTalk on the next several slides.
343
891000
4000
bih mogao da održim ceo TEDTalk samo o sledećih nekoliko slajdova.
15:13
We had to create a lighting system.
344
895000
3000
Morali smo da napravimo sistem rasvete.
15:16
So really, a big part of our processes was creating a lighting environment
345
898000
3000
Veliki deo našeg rada je bilo pravljenje svetlosnog okruženja
15:19
for every single location that Benjamin had to appear
346
901000
2000
za svaku lokaciju na kojoj je Bendžamin trebalo da se pojavi
15:21
so that we could put Ben's head into any scene
347
903000
3000
kako bismo stavili njegovu glavu u svaku scenu
15:24
and it would exactly match the lighting that's on the other actors
348
906000
3000
i ona bi se tačno poklopila sa osvetljenjem na drugim
15:27
in the real world.
349
909000
1000
glumcima u realnom svetu.
15:28
We also had to create an eye system.
350
910000
3000
Morali smo da napravimo i sistem za oči.
15:31
We found the old adage, you know,
351
913000
2000
Otkrili smo da je stara poslovica,
15:33
"The eyes are the window to the soul,"
352
915000
2000
"Oči su ogledalo duše"
15:35
absolutely true.
353
917000
1000
potpuno istinita.
15:36
So the key here was to keep everybody looking in Ben's eyes.
354
918000
2000
Ključ je bio da svi gledaju u Benove oči.
15:38
And if you could feel the warmth, and feel the humanity,
355
920000
2000
Ako možete da osetite toplinu i čovečnost,
15:40
and feel his intent coming through the eyes,
356
922000
3000
i njegovu nameru kroz njegove oči,
15:43
then we would succeed.
357
925000
1000
onda smo uspeli.
15:44
So we had one person focused on the eye system
358
926000
3000
Jedna osoba je bila fokusirana na oči,
15:47
for almost two full years.
359
929000
2000
skoro pune dve godine.
15:49
We also had to create a mouth system.
360
931000
2000
Morali smo da napravimo i sistem za usta.
15:51
We worked from dental molds of Brad.
361
933000
2000
Radili smo sa Bredovim dentalnim kalupima.
15:53
We had to age the teeth over time.
362
935000
2000
Trebalo je da zubi ostare tokom vremena.
15:55
We also had to create an articulating tongue that allowed him to enunciate his words.
363
937000
3000
Morali smo da napravimo jezik koji dozvoljava izgovaranje reči.
15:58
There was a whole system written in software to articulate the tongue.
364
940000
2000
Ceo jedan sistem u softveru je bio zadužen za jezik.
16:00
We had one person devoted to the tongue for about nine months.
365
942000
2000
Jedna osoba je bila zadužena za jezik tokom devet meseci.
16:02
He was very popular.
366
944000
2000
Bio je veoma popularan.
16:04
Skin displacement: another big deal.
367
946000
3000
Pomeranje kože: još jedna bitna stvar.
16:07
The skin had to be absolutely accurate.
368
949000
2000
Koža je morala da bude potpuno odgovarajuća.
16:09
He's also in an old age home, he's in a nursing home
369
951000
3000
On se nalazi i u staračkom domu,
16:12
around other old people,
370
954000
2000
okružen drugim starcima,
16:14
so he had to look exactly the same as the others.
371
956000
2000
pa je morao da izgleda potpuno isto kao oni.
16:16
So, lots of work on skin deformation,
372
958000
1000
Mnogo rada na deformaciji kože,
16:17
you can see in some of these cases it works,
373
959000
1000
vidite da u nekim slučajevima uspeva,
16:18
in some cases it looks bad.
374
960000
1000
a negde izgleda loše.
16:19
This is a very, very, very early test in our process.
375
961000
2000
Ovo je test iz vrlo, vrlo rane faze u našem procesu.
16:21
So, effectively we created a digital puppet
376
963000
3000
Bukvalno smo kreirali digitalnu lutku
16:24
that Brad Pitt could operate with his own face.
377
966000
3000
kojom je Bred Pit mogao da upravlja svojim licem.
16:27
There were no animators necessary to come in and interpret behavior
378
969000
4000
Nisu bili potrebni animatori koji bi interpretirali ponašanje
16:31
or enhance his performance.
379
973000
2000
ili pojačali njegovo izvođenje.
16:33
There was something that we encountered, though,
380
975000
3000
Ipak smo naišli na nešto, što smo
16:36
that we ended up calling "the digital Botox effect."
381
978000
3000
na kraju zvali "digitalni efekat botoksa".
16:39
So, as things went through this process,
382
981000
3000
Kako su stvari prolazile kroz ovaj proces,
16:42
Fincher would always say, "It sandblasts the edges off of the performance."
383
984000
3000
Finčer bi uvek rekao "To šmirgla ivice izvođenja".
16:45
And thing our process and the technology couldn't do,
384
987000
3000
Naš proces i tehnologija nisu mogli
16:48
is they couldn't understand intent,
385
990000
3000
da razumeju nameru
16:51
the intent of the actor.
386
993000
2000
glumca.
16:53
So it sees a smile as a smile.
387
995000
2000
Oni osmeh vide kao osmeh.
16:55
It doesn't recognize an ironic smile, or a happy smile,
388
997000
3000
Ne prepoznaju ironični osmeh, srećni osmeh,
16:58
or a frustrated smile.
389
1000000
1000
frustrirani osmeh.
16:59
So it did take humans to kind of push it one way or another.
390
1001000
3000
Ipak su bili potrebni ljudi da bi uredili detalje.
17:02
But we ended up calling the entire process
391
1004000
3000
Na kraju smo ceo proces i svu tehnologiju
17:05
and all the technology "emotion capture,"
392
1007000
2000
zvali "beleženje emocija",
17:07
as opposed to just motion capture.
393
1009000
1000
nasuprot beleženju pokreta.
17:08
Take another look.
394
1010000
2000
Pogledajte još jednom.
17:11
Brad Pitt: Well, I heard momma and Tizzy whisper,
395
1013000
2000
Bred Pit: Pa, čuo sam da mama i Tizi šapuću
17:13
and they said I was gonna die soon,
396
1015000
2000
kako ću uskoro da umrem,
17:15
but ... maybe not.
397
1017000
2000
ali... možda i neću.
17:37
EU: That's how to create a digital human in 18 minutes.
398
1039000
3000
EU: Tako se kreira digitalni čovek, u 18 minuta.
17:40
(Applause)
399
1042000
3000
(aplauz)
17:48
A couple of quick factoids;
400
1050000
2000
Par kratkih činjenica:
17:50
it really took 155 people over two years,
401
1052000
4000
zaista je bilo potrebno 155 ljudi tokom dve godine,
17:54
and we didn't even talk about 60 hairstyles and an all-digital haircut.
402
1056000
4000
a nisam čak ni pomenuo 60 frizura i potpuno digitalno šišanje.
17:58
But, that is Benjamin. Thank you.
403
1060000
3000
Ali, to je Bendžamin. Hvala vam.
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