I'm here today representing a team of artists and technologists and filmmakers that worked together on a remarkable film project for the last four years. And along the way they created a breakthrough in computer visualization.
Danas ovde predstavljam tim umetnika, tehničara i filmadžija, koji su zajedno radili na izuzetnom filmskom projektu u poslednje četiri godine. Tokom tog rada, napravili su proboj u kompjuterskoj vizualizaciji.
So I want to show you a clip of the film now. Hopefully it won't stutter. And if we did our jobs well, you won't know that we were even involved.
Sada želim da vam pokažem insert iz filma. Nadam se da neće zastajkivati. I ako smo dobro uradili svoje poslove, nećete ni znati da smo bili prisutni.
Voice (Video): I don't know how it's possible ... but you seem to have more hair.
Glas (video): Ne znam da li je moguće -- ali izgleda da imaš više kose.
Brad Pitt: What if I told you that I wasn't getting older ... but I was getting younger than everybody else?
Bred Pit: Šta bi bilo kad bih ti rekao da ja ne starim... nego postajem mlađi od svih ostalih?
I was born with some form of disease.
Rođen sam s nekom vrstom bolesti.
Voice: What kind of disease?
Glas: Kakvom vrstom bolesti?
BP: I was born old.
BP: Rođen sam star.
Man: I'm sorry.
Čovek: Žao mi je.
BP: No need to be. There's nothing wrong with old age.
BP: Nema potrebe. Nema ništa loše sa starošću.
Girl: Are you sick?
Devojčica: Da li si bolestan?
BP: I heard momma and Tizzy whisper, and they said I was gonna die soon. But ... maybe not.
BP: Čuo sam da mama i Tizi šapuću kako ću uskoro da umrem. Ali... možda i neću.
Girl: You're different than anybody I've ever met.
Devojčica: Ti si drugačiji od svih koje znam.
BB: There were many changes ... some you could see, some you couldn't. Hair started growing in all sorts of places, along with other things. I felt pretty good, considering.
BP: Bilo je mnogo promena... neke su bile primetne, druge ne. Dlake su počele da rastu na svakakvim mestima, kao i neke druge stvari. S obzirom na sve, osećao sam se prilično dobro.
Ed Ulbrich: That was a clip from "The Curious Case of Benjamin Button." Many of you, maybe you've seen it or you've heard of the story, but what you might not know is that for nearly the first hour of the film, the main character, Benjamin Button, who's played by Brad Pitt, is completely computer-generated from the neck up. Now, there's no use of prosthetic makeup or photography of Brad superimposed over another actor's body. We've created a completely digital human head.
Ed Ulbrih: To je insert iz "Čudesnog slučaja Bendžamina Batona". Mnogi od vas su ga možda već videli ili čuli priču, ali ono što ne znate je da je, tokom skoro celog prvog sata filma, glavni junak, Bendžamin Baton, koga igra Bred Pit, u potpunosti kompjuterski generisan od vrata na gore. Scenska šminka nije bila od koristi, kao ni Bredova fotografija, montirana na telo drugog glumca. Stvorili smo potpuno digitalnu ljudsku glavu.
So I'd like to start with a little bit of history on the project. This is based on an F. Scott Fitzgerald short story. It's about a man who's born old and lives his life in reverse. Now, this movie has floated around Hollywood for well over half a century, and we first got involved with the project in the early '90s, with Ron Howard as the director. We took a lot of meetings and we seriously considered it. But at the time we had to throw in the towel. It was deemed impossible. It was beyond the technology of the day to depict a man aging backwards. The human form, in particular the human head, has been considered the Holy Grail of our industry.
Počeću sa istorijskim podacima o projektu. Film je baziran na kratkoj priči F. Skota Ficdžeralda. Radi se o čoveku koji je rođen star i živi život unazad. Ovaj film je kružio Holivudom više od pola veka, a mi smo se prvi put uključili ranih devedesetih, kada je Ron Hauard bio režiser. Imali smo mnogo sastanaka i ozbiljno smo razmišljali o tome. Ali u to vreme smo morali da odustanemo. Procenili smo da je nemoguće. Tehnologija tog vremena nije mogla da prikaže čovekovo starenje unazad. Ljudski oblik, a naročito glava, smatrana je za Sveti Gral naše industrije.
The project came back to us about a decade later, and this time with a director named David Fincher. Now, Fincher is an interesting guy. David is fearless of technology, and he is absolutely tenacious. And David won't take "no." And David believed, like we do in the visual effects industry, that anything is possible as long as you have enough time, resources and, of course, money. And so David had an interesting take on the film, and he threw a challenge at us. He wanted the main character of the film to be played from the cradle to the grave by one actor. It happened to be this guy.
Oko deset godina kasnije projekat nam se vratio, a ovog puta je režiser bio Dejvid Finčer. Finčer je zanimljiv tip. On se ne boji tehnologije, i vrlo je uporan. Ne prihvata "ne" kao odgovor. Dejvid je, kao i mi u industriji vizuelnih efekata, verovao da je sve moguće, ako imate dovoljno vremena, resursa i naravno, novca. Dejvid je imao zanimljiv pogled na film i postavio nam je izazov. Želeo je da glavnog lika u filmu, od kolevke do groba, igra jedan glumac. Desilo se da je to ovaj momak.
We went through a process of elimination and a process of discovery with David, and we ruled out, of course, swapping actors. That was one idea: that we would have different actors, and we would hand off from actor to actor.
Sa Dejvidom smo prošli procese eliminacije i otkrivanja i naravno, odbacili smo ideju zamene glumaca. To je bila jedna ideja: mogli smo imati različite glumce, i snimali bismo naizmenično.
We even ruled out the idea of using makeup. We realized that prosthetic makeup just wouldn't hold up, particularly in close-up. And makeup is an additive process. You have to build the face up. And David wanted to carve deeply into Brad's face to bring the aging to this character. He needed to be a very sympathetic character. So we decided to cast a series of little people that would play the different bodies of Benjamin at the different increments of his life and that we would in fact create a computer-generated version of Brad's head, aged to appear as Benjamin, and attach that to the body of the real actor. Sounded great.
Čak smo odbacili ideju o korišćenju šminke. Shvatili smo da scenska šminka neće uspeti, naročito u krupnim kadrovima. Šminka je slojevit proces. Morate da izgradite lice. A Dejvid je želeo da duboko ureže u Bredovo lice, da bi njegov lik ostario. Morao je da bude i vrlo simpatičan karakter. Zato smo odlučili da odaberemo nekoliko niskih ljudi koji bi igrali različita Bendžaminova tela, u različitim fazama njegovog života, a da kompjuterski napravimo verziju Bredove glave da po godinama podseća na Bendžamina, i "povežemo" je na telo pravog glumca. Zvučalo je super.
Of course, this was the Holy Grail of our industry, and the fact that this guy is a global icon didn't help either, because I'm sure if any of you ever stand in line at the grocery store, you know -- we see his face constantly. So there really was no tolerable margin of error. There were two studios involved: Warner Brothers and Paramount. And they both believed this would make an amazing film, of course, but it was a very high-risk proposition. There was lots of money and reputations at stake. But we believed that we had a very solid methodology that might work ...
Naravno, to je bio Sveti Gral naše industrije, a nije pomagala ni činjenica da je ovaj momak globalna ikona, jer sam siguran da ako nekad stojite u redu u prodavnici -- njegovo lice stalno viđamo. Dakle, uopšte nije bilo mesta za grešku. Učestvovala su dva studija: "Warner Brothers" i "Paramount". Naravno, oba su verovala da će ovo biti izuzetan film, ali to je bio posao visokog rizika. Mnogo je novca i reputacija bilo na kocki. Ali mi smo verovali da imamo jako dobru metodologiju koja bi mogla da uspe...
But despite our verbal assurances, they wanted some proof. And so, in 2004, they commissioned us to do a screen test of Benjamin. And we did it in about five weeks. But we used lots of cheats and shortcuts. We basically put something together to get through the meeting. I'll roll that for you now. This was the first test for Benjamin Button. And in here, you can see, that's a computer-generated head -- pretty good -- attached to the body of an actor. And it worked. And it gave the studio great relief. After many years of starts and stops on this project, and making that tough decision, they finally decided to greenlight the movie. And I can remember, actually, when I got the phone call to congratulate us, to say the movie was a go, I actually threw up. (Laughter) You know, this is some tough stuff.
Ali i pored naših verbalnih uveravanja, oni su hteli neke dokaze. Tako su 2004. tražili od nas da uradimo probnu ekranizaciju Bendžamina. Uradili smo je za otprilike pet nedelja. Ali dosta smo varali i koristili prečice. U stvari, samo smo nešto sklepali kako bismo prošli sastanak. Sad ću vam to pustiti. Ovo je prvi test Bendžamina Batona. Ovde možete videti da je to kompjuterski generisana glava - prilično dobra - montirana na telo nekog glumca. I uspelo je. Studiju je bilo mnogo lakše. Posle dugogodišnjih započinjanja i pauza, i donošenja teških odluka o ovom projektu, konačno su odlučili da filmu daju zeleno svetlo. Zapravo, sećam se telefonskog razgovora u kom su nam čestitali, kad su rekli da će se snimati, povratio sam. (smeh) Znate, ovo je vrlo ozbiljan posao.
So we started to have early team meetings, and we got everybody together, and it was really more like therapy in the beginning, convincing each other and reassuring each other that we could actually undertake this. We had to hold up an hour of a movie with a character. And it's not a special effects film; it has to be a man. We really felt like we were in a -- kind of a 12-step program. And of course, the first step is: admit you've got a problem. (Laughter) So we had a big problem: we didn't know how we were going to do this. But we did know one thing. Being from the visual effects industry, we, with David, believed that we now had enough time, enough resources, and, God, we hoped we had enough money. And we had enough passion to will the processes and technology into existence.
Počeli smo sa ranim sastancima tima, okupili smo sve ljude, na početku je to bilo više kao terapija, ubeđivali smo i uveravali jedni druge da možemo ovo da izvedemo. Trebalo je da stvorimo sat vremena filma sa nekim likom. To nije film sa specijalnim efektima; mora da bude čovek. Stvarno smo se osećali kao da smo u nekom programu od 12 koraka. Naravno, prvi korak je: priznaj da imaš problem. (smeh) Imali smo veliki problem: nismo znali kako ćemo ovo da uradimo. Ali znali smo jednu stvar: pošto potičemo iz industrije vizuelnih efekata, i mi i Dejvid smo mislili da imamo dovoljno vremena, resursa i Bože, nadali smo se da imamo dovoljno novca. A imali smo i dovoljno strasti da oživimo procese i tehnologiju.
So, when you're faced with something like that, of course you've got to break it down. You take the big problem and you break it down into smaller pieces and you start to attack that. So we had three main areas that we had to focus on. We needed to make Brad look a lot older -- needed to age him 45 years or so. And we also needed to make sure that we could take Brad's idiosyncrasies, his little tics, the little subtleties that make him who he is and have that translate through our process so that it appears in Benjamin on the screen.
Kada ste suočeni sa nečim takvim, naravno da morate da ga razložite na delove. Uzmete veliki problem i raščlanite ga na manje delove i počnete njih da napadate. Imali smo tri glavne celine na koje je trebalo da se fokusiramo. Da učinimo da Bred izgleda mnogo starije - da ostari oko 45 godina. I trebalo je da budemo sigurni da ćemo uhvatiti njegove specifičnosti, njegove male tikove, nijanse koje ga čine onim ko je, i preneti ih kroz naš proces da bi se na ekranu pojavile u Bendžaminu.
And we also needed to create a character that could hold up under, really, all conditions. He needed to be able to walk in broad daylight, at nighttime, under candlelight, he had to hold an extreme close-up, he had to deliver dialogue, he had to be able to run, he had to be able to sweat, he had to be able to take a bath, to cry, he even had to throw up. Not all at the same time -- but he had to, you know, do all of those things.
I trebalo je da napravimo lik koji bi izdržao stvarno sve uslove. Da može da hoda usred bela dana, noću, pod svetlošću sveće, morao je da bude u izuzetno krupnom planu, da učestvuje u razgovoru, da može da trči, da se znoji, da se kupa, da plače, čak je trebalo da povraća. Ne sve u isto vreme - ali je trebalo da radi sve te stvari.
And the work had to hold up for almost the first hour of the movie. We did about 325 shots. So we needed a system that would allow Benjamin to do everything a human being can do. And we realized that there was a giant chasm between the state of the art of technology in 2004 and where we needed it to be.
Taj rad je morao da izdrži skoro tokom prvog sata filma. Uradili smo oko 325 snimaka. Bio nam je potreban sistem koji bi omogućio Bendžaminu da radi sve što ljudsko biće može da radi. Shvatili smo da postoji ogroman jaz između toga gde se tehnologija nalazila 2004. godine i onoga gde je trebalo da bude za naše potrebe.
So we focused on motion capture. I'm sure many of you have seen motion capture. The state of the art at the time was something called marker-based motion capture. I'll give you an example here. It's basically the idea of, you wear a leotard, and they put some reflective markers on your body, and instead of using cameras, there're infrared sensors around a volume, and those infrared sensors track the three-dimensional position of those markers in real time. And then animators can take the data of the motion of those markers and apply them to a computer-generated character. You can see the computer characters on the right are having the same complex motion as the dancers.
Fokusirali smo se na snimanje pokreta. Siguran sam da su mnogi od vas to videli. U to vreme je vrhunska umetnost bila nešto što se zove snimanje pokreta na osnovu markera. Daću vam jedan primer. Ideja je da nosite triko, a na vaše telo se postave reflektujući označivači - markeri i umesto da se koriste kamere, tu su infracrveni senzori koji u realnom vremenu prate trodimenzionalnu poziciju tih markera. Potom animatori mogu uzeti podatke o kretanju iz tih markera i primeniti ih na kompjuterski generisan lik. Vidite da kompjuterski generisani likovi s desne strane izvode iste složene pokrete kao i plesači.
But we also looked at numbers of other films at the time that were using facial marker tracking, and that's the idea of putting markers on the human face and doing the same process. And as you can see, it gives you a pretty crappy performance. That's not terribly compelling. And what we realized was that what we needed was the information that was going on between the markers. We needed the subtleties of the skin. We needed to see skin moving over muscle moving over bone. We needed creases and dimples and wrinkles and all of those things.
Takođe smo gledali i veliki broj drugih filmova koji su tada koristili praćenje pokreta lica, a to je ideja da se označivači stave na lice i obavi se isti proces. Kao što vidite, dobijate prilično jadan rezultat. To nije baš ubedljivo. Shvatili smo da su nam potrebne informacije o dešavanjima između markera. Potrebni su nam detalji kože. Trebalo je da vidimo pokrete kože preko mišića i kostiju. Trebale su nam linije, rupice, bore, sve te stvari.
Our first revelation was to completely abort and walk away from the technology of the day, the status quo, the state of the art. So we aborted using motion capture. And we were now well out of our comfort zone, and in uncharted territory. So we were left with this idea that we ended up calling "technology stew." We started to look out in other fields. The idea was that we were going to find nuggets or gems of technology that come from other industries like medical imaging, the video game space, and re-appropriate them. And we had to create kind of a sauce. And the sauce was code in software that we'd written to allow these disparate pieces of technology to come together and work as one.
Naše prvo otkrovenje bilo je da u potpunosti odustanemo od tadašnje tehnologije, statusa kvo, vrhunske umetnosti. Odustali smo od korišćenja snimanja pokreta. Sada smo već bili prilično izvan zone udobnosti, na neobeleženoj teritoriji. Ostali smo sa idejom koju smo na kraju zvali "tehnološki paprikaš". Počeli smo da istražujemo u drugim poljima. Ideja je bila da pronađemo komadiće, dragulje tehnologije koji dolaze iz drugih industrija kao što su medicina ili video igre i da ih prilagodimo. Trebalo je da napravimo neku vrstu sosa. A sos je bio kod u softveru, koji smo napisali kako bismo omogućili da se ovi različiti delovi tehnologije spoje i funkcionišu kao jedan.
Initially, we came across some remarkable research done by a gentleman named Dr. Paul Ekman in the early '70s. He believed that he could, in fact, catalog the human face. And he came up with this idea of Facial Action Coding System, or FACS. He believed that there were 70 basic poses or shapes of the human face, and that those basic poses or shapes of the face can be combined to create infinite possibilities of everything the human face is capable of doing. And of course, these transcend age, race, culture, gender. So this became the foundation of our research as we went forward.
Prvo smo naišli na izuzetno istraživanje koje je sproveo gospodin po imenu dr Pol Ekman, ranih '70-ih. On je verovao da može da katalogizuje ljudsko lice. Osmislio je Sistem kodiranja facijalne akcije, SKFA. Smatrao je da postoji sedamdeset osnovnih poza ili oblika ljudskog lica, i da te osnovne poze ili oblici mogu da se kombinuju i stvore nebrojene mogućnosti svega što je ljudsko lice sposobno da uradi. Naravno, oni su nezavisni od godina, rase, kulture, pola. Kako smo napredovali, to je postala osnova našeg istraživanja.
And then we came across some remarkable technology called Contour. And here you can see a subject having phosphorus makeup stippled on her face. And now what we're looking at is really creating a surface capture as opposed to a marker capture. The subject stands in front of a computer array of cameras, and those cameras can, frame-by-frame, reconstruct the geometry of exactly what the subject's doing at the moment. So, effectively, you get 3D data in real time of the subject. And if you look in a comparison, on the left, we see what volumetric data gives us and on the right you see what markers give us. So, clearly, we were in a substantially better place for this. But these were the early days of this technology, and it wasn't really proven yet. We measure complexity and fidelity of data in terms of polygonal count. And so, on the left, we were seeing 100,000 polygons. We could go up into the millions of polygons. It seemed to be infinite.
Onda smo naišli na jednu izuzetnu tehnologiju po imenu "Kontura". Ovde vidite da subjekt ima fosfornu šminku nanesenu na lice. Sada zapravo možemo da snimimo povšinu, umesto snimanja samo označivača. Ovaj subjekt stoji ispred kompjuterskih kamera i one mogu, kadar po kadar, da rekonstruišu geometriju upravo onoga što subjekt radi u trenutku. Bukvalno dobijate 3D podatke o subjektu u realnom vremenu. Ako pogledamo uporedo, levo vidimo šta nam podaci o zapremini daju, a desno vidimo šta nam označivači daju. Jasno je da smo bili u mnogo boljem položaju za ovo. Ali to su bili rani dani te tehnologije i još nije bila dokazana. Merimo složenost i preciznost podataka u smislu broja poligona. Tako, s leve strane imamo 100 000 poligona. Mogli bismo da dostignemo milione poligona. Izgledalo je neograničeno.
This was when we had our "Aha!" This was the breakthrough. This is when we're like, "OK, we're going to be OK, This is actually going to work." And the "Aha!" was, what if we could take Brad Pitt, and we could put Brad in this device, and use this Contour process, and we could stipple on this phosphorescent makeup and put him under the black lights, and we could, in fact, scan him in real time performing Ekman's FACS poses. Right? So, effectively, we ended up with a 3D database of everything Brad Pitt's face is capable of doing. (Laughter)
Tada smo doživeli "Aha!" trenutak. To je bio proboj. Tada smo pomislili, "OK, bićemo dobro. Ovo će zaista uspeti." A "Aha!" je bilo: šta ako bismo uzeli Breda i stavili ga u ovu spravu i iskoristili "Kontura" proces i naneli mu fluorescentnu šminku i stavili ga pod "blacklight" - mogli bismo da ga skeniramo u realnom vremenu koristeći Ekmanove SKFA poze. Je l' tako? Dakle, bukvalno smo dobili 3D bazu podataka svih pokreta koje je lice Breda Pita u stanju da uradi. (smeh)
From there, we actually carved up those faces into smaller pieces and components of his face. So we ended up with literally thousands and thousands and thousands of shapes, a complete database of all possibilities that his face is capable of doing.
Odatle smo isekli ta lica na manje delove i komponente njegovog lica. Dobili smo bukvalno hiljade i hiljade i hiljade oblika, kompletnu bazu podataka svih mogućnosti koje ovo lice može da izvede.
Now, that's great, except we had him at age 44. We need to put another 40 years on him at this point. We brought in Rick Baker, and Rick is one of the great makeup and special effects gurus of our industry. And we also brought in a gentleman named Kazu Tsuji, and Kazu Tsuji is one of the great photorealist sculptors of our time. And we commissioned them to make a maquette, or a bust, of Benjamin. So, in the spirit of "The Great Unveiling" -- I had to do this -- I had to unveil something. So this is Ben 80. We created three of these: there's Ben 80, there's Ben 70, there's Ben 60. And this really became the template for moving forward.
To je super, ali mi smo ga snimili sa 44 godine. Tada je trebalo da mu dodamo još 40 godina. Doveli smo Rika Bejkera, koji je jedan od odličnih gurua za šminku i specijalne efekte u našoj industriji. Doveli smo i gospodina po imenu Kazu Tsudži, a on je jedan od najboljih fotorealističnih skulptora našeg vremena. Tražili smo od njih da naprave maketu, bistu Bendžamina. U duhu "Velikog otkrivanja" - morao sam ovo da uradim - morao sam nešto da otkrijem. Ovo je Ben 80. Napravili smo tri ovakva: imamo Bena 80, Bena 70, Bena 60. Ovo je postao šablon za napredovanje.
Now, this was made from a life cast of Brad. So, in fact, anatomically, it is correct. The eyes, the jaw, the teeth: everything is in perfect alignment with what the real guy has. We have these maquettes scanned into the computer at very high resolution -- enormous polygonal count. And so now we had three age increments of Benjamin in the computer.
Ovo je napravljeno od pravog odlivka Breda. Dakle, anatomski je tačno. Oči, vilica, zubi: sve se savršeno poklapa sa pravim čovekom. Skenirali smo ove makete sa veoma visokom rezolucijom - imaju ogroman broj poligona. Sada smo u kompjuteru imali Bendžamina u tri starosne verzije.
But we needed to get a database of him doing more than that. We went through this process, then, called retargeting. This is Brad doing one of the Ekman FACS poses. And here's the resulting data that comes from that, the model that comes from that. Retargeting is the process of transposing that data onto another model. And because the life cast, or the bust -- the maquette -- of Benjamin was made from Brad, we could transpose the data of Brad at 44 onto Brad at 87. So now, we had a 3D database of everything Brad Pitt's face can do at age 87, in his 70s and in his 60s.
Ali bila nam je potrebna baza sa više pokreta. Prošli smo kroz proces koji se zove ponovno mapiranje. Ovde Bred izvodi jednu od Ekmanovih SKFA poza. A evo podataka koji su rezultat toga, model koji iz toga nastaje. Ponovno mapiranje je proces prenošenja tih podataka na drugi model. Budući da je model Bendžamina - bista ili maketa - napravljena od Breda, mogli smo da prenesemo podatke Breda sa 44 godine, na onog sa 87. Sada smo imali bazu svega što Bredovo lice može da uradi u 87. godini, u sedamdesetim i šezdesetim.
Next we had to go into the shooting process. So while all that's going on, we're down in New Orleans and locations around the world. And we shot our body actors, and we shot them wearing blue hoods. So these are the gentleman who played Benjamin. And the blue hoods helped us with two things: one, we could easily erase their heads; and we also put tracking markers on their heads so we could recreate the camera motion and the lens optics from the set.
Potom je trebalo da pređemo na snimanje. Dok se sve to dešava, mi se nalazimo u Nju Orleansu i lokacijama širom sveta. Snimali smo tela drugih glumaca dok su nosili plave kapuljače. Ovo su sve gospoda koja su igrala Bendžamina. Plave kapuljače su nam pomogle na dva načina: Prvo, tako smo lako mogli da izbrišemo njihove glave; a takođe smo im stavili markere pokreta na glave, kako bismo ponovili pokrete kamere i optiku sa snimanja.
But now we needed to get Brad's performance to drive our virtual Benjamin. And so we edited the footage that was shot on location with the rest of the cast and the body actors and about six months later we brought Brad onto a sound stage in Los Angeles and he watched on the screen. His job, then, was to become Benjamin. And so we looped the scenes. He watched again and again. We encouraged him to improvise. And he took Benjamin into interesting and unusual places that we didn't think he was going to go. We shot him with four HD cameras so we'd get multiple views of him and then David would choose the take of Brad being Benjamin that he thought best matched the footage with the rest of the cast.
Zatim je Bredovo izvođenje trebalo da pokreće virtualnog Bendžamina. Montirali smo snimke sa lokacija sa ostatkom ekipe i glumcima-telima i oko šest meseci kasnije doveli smo Breda u zvučni studio u Los Anđelesu i on je gledao na ekranu. Njegov posao je onda bio da postane Bendžamin. Ponavljali smo scene. Gledao je iznova i iznova. Podsticali smo ga da improvizuje. Odveo je Bendžamina na zanimljiva i neobična mesta na koja nismo mislili da će ga povesti. Snimali smo ga sa 4 kamere visoke rezolucije kako bismo imali više uglova a onda bi Dejvid odabrao snimak Breda kao Bendžamina za koji je mislio da se najbolje uklapa sa ostalim glumcima.
From there we went into a process called image analysis. And so here, you can see again, the chosen take. And you are seeing, now, that data being transposed on to Ben 87. And so, what's interesting about this is we used something called image analysis, which is taking timings from different components of Benjamin's face. And so we could choose, say, his left eyebrow. And the software would tell us that, well, in frame 14 the left eyebrow begins to move from here to here, and it concludes moving in frame 32. And so we could choose numbers of positions on the face to pull that data from.
Odatle smo prešli u proces analize snimka. Ovde opet vidite izabrani snimak. Ovde vidite kako se on prenosi na Bena sa 87 godina. Zanimljivo je ovde da smo koristili analizu snimka, koja uzima vremenske tačke različitih komponenti Bendžaminovog lica. Mogli smo, recimo, da odaberemo njegovu levu obrvu. A softver bi nam rekao kako u 14. slici leva obrva počinje da se kreće i kako završava pokret u 32. slici. Mogli smo da izaberemo broj pozicija na licu iz kojih smo uzimali podatke.
And then, the sauce I talked about with our technology stew -- that secret sauce was, effectively, software that allowed us to match the performance footage of Brad in live action with our database of aged Benjamin, the FACS shapes that we had. On a frame-by-frame basis, we could actually reconstruct a 3D head that exactly matched the performance of Brad.
A onda, sos o kom sam govorio u našem tehnološkom paprikašu - tajni sos je bio, bukvalno, softver koji je omogućio da povežemo snimak Bredovog izvođenja uživo, sa bazom podataka starog Bendžamina, SKFA pozama koje smo imali. Na nivou jedne-po-jedne slike, mogli smo da rekonstruišemo 3D glavu koja se potpuno poklapala sa Bredovim izvođenjem.
So this was how the finished shot appeared in the film. And here you can see the body actor. And then this is what we called the "dead head," no reference to Jerry Garcia.
Ovako je završeni snimak izgledao na filmu. Možete videti glumca za telo. Ovo smo zvali "mrtva glava", što nema veze sa Džerijem Garsijom.
And then here's the reconstructed performance now with the timings of the performance. And then, again, the final shot. It was a long process. (Applause)
A evo i rekonstruisanog izvođenja zajedno sa vremenskim zapisom izvođenja. I ponovo, konačni snimak. Bio je to dug proces. (aplauz)
The next section here, I'm going to just blast through this, because we could do a whole TEDTalk on the next several slides.
Brzo ću proći kroz sledeći deo jer bih mogao da održim ceo TEDTalk samo o sledećih nekoliko slajdova.
We had to create a lighting system. So really, a big part of our processes was creating a lighting environment for every single location that Benjamin had to appear so that we could put Ben's head into any scene and it would exactly match the lighting that's on the other actors in the real world.
Morali smo da napravimo sistem rasvete. Veliki deo našeg rada je bilo pravljenje svetlosnog okruženja za svaku lokaciju na kojoj je Bendžamin trebalo da se pojavi kako bismo stavili njegovu glavu u svaku scenu i ona bi se tačno poklopila sa osvetljenjem na drugim glumcima u realnom svetu.
We also had to create an eye system. We found the old adage, you know, "The eyes are the window to the soul," absolutely true. So the key here was to keep everybody looking in Ben's eyes. And if you could feel the warmth, and feel the humanity, and feel his intent coming through the eyes, then we would succeed. So we had one person focused on the eye system for almost two full years.
Morali smo da napravimo i sistem za oči. Otkrili smo da je stara poslovica, "Oči su ogledalo duše" potpuno istinita. Ključ je bio da svi gledaju u Benove oči. Ako možete da osetite toplinu i čovečnost, i njegovu nameru kroz njegove oči, onda smo uspeli. Jedna osoba je bila fokusirana na oči, skoro pune dve godine.
We also had to create a mouth system. We worked from dental molds of Brad. We had to age the teeth over time.
Morali smo da napravimo i sistem za usta. Radili smo sa Bredovim dentalnim kalupima. Trebalo je da zubi ostare tokom vremena.
We also had to create an articulating tongue that allowed him to enunciate his words. There was a whole system written in software to articulate the tongue. We had one person devoted to the tongue for about nine months. He was very popular.
Morali smo da napravimo jezik koji dozvoljava izgovaranje reči. Ceo jedan sistem u softveru je bio zadužen za jezik. Jedna osoba je bila zadužena za jezik tokom devet meseci. Bio je veoma popularan.
Skin displacement: another big deal. The skin had to be absolutely accurate. He's also in an old age home, he's in a nursing home around other old people, so he had to look exactly the same as the others. So, lots of work on skin deformation, you can see in some of these cases it works, in some cases it looks bad. This is a very, very, very early test in our process. So, effectively we created a digital puppet that Brad Pitt could operate with his own face. There were no animators necessary to come in and interpret behavior or enhance his performance.
Pomeranje kože: još jedna bitna stvar. Koža je morala da bude potpuno odgovarajuća. On se nalazi i u staračkom domu, okružen drugim starcima, pa je morao da izgleda potpuno isto kao oni. Mnogo rada na deformaciji kože, vidite da u nekim slučajevima uspeva, a negde izgleda loše. Ovo je test iz vrlo, vrlo rane faze u našem procesu. Bukvalno smo kreirali digitalnu lutku kojom je Bred Pit mogao da upravlja svojim licem. Nisu bili potrebni animatori koji bi interpretirali ponašanje ili pojačali njegovo izvođenje.
There was something that we encountered, though, that we ended up calling "the digital Botox effect." So, as things went through this process, Fincher would always say, "It sandblasts the edges off of the performance." And thing our process and the technology couldn't do, is they couldn't understand intent, the intent of the actor. So it sees a smile as a smile. It doesn't recognize an ironic smile, or a happy smile, or a frustrated smile. So it did take humans to kind of push it one way or another.
Ipak smo naišli na nešto, što smo na kraju zvali "digitalni efekat botoksa". Kako su stvari prolazile kroz ovaj proces, Finčer bi uvek rekao "To šmirgla ivice izvođenja". Naš proces i tehnologija nisu mogli da razumeju nameru glumca. Oni osmeh vide kao osmeh. Ne prepoznaju ironični osmeh, srećni osmeh, frustrirani osmeh. Ipak su bili potrebni ljudi da bi uredili detalje.
But we ended up calling the entire process and all the technology "emotion capture," as opposed to just motion capture. Take another look.
Na kraju smo ceo proces i svu tehnologiju zvali "beleženje emocija", nasuprot beleženju pokreta. Pogledajte još jednom.
Brad Pitt: Well, I heard momma and Tizzy whisper, and they said I was gonna die soon, but ... maybe not.
Bred Pit: Pa, čuo sam da mama i Tizi šapuću kako ću uskoro da umrem, ali... možda i neću.
EU: That's how to create a digital human in 18 minutes. (Applause)
EU: Tako se kreira digitalni čovek, u 18 minuta. (aplauz)
A couple of quick factoids; it really took 155 people over two years, and we didn't even talk about 60 hairstyles and an all-digital haircut. But, that is Benjamin. Thank you.
Par kratkih činjenica: zaista je bilo potrebno 155 ljudi tokom dve godine, a nisam čak ni pomenuo 60 frizura i potpuno digitalno šišanje. Ali, to je Bendžamin. Hvala vam.