WEBVTT

00:00:00.775 --> 00:00:02.541
I love making movies.

00:00:05.174 --> 00:00:09.373
Motion pictures have been in existence
for more than a hundred years.

00:00:10.370 --> 00:00:14.029
Filmmaking hasn't changed
for the dimensional mindset.

00:00:15.092 --> 00:00:19.430
Placing the camera in a scene
and pressing "record" hasn't changed.

00:00:19.454 --> 00:00:22.699
Filmmaking is still a frontal experience,

00:00:22.723 --> 00:00:25.859
and creating the film has the possibility

00:00:25.883 --> 00:00:30.062
to follow the same direction
of the content creation.

00:00:30.086 --> 00:00:33.167
We still stand in front of a flat image,

00:00:33.191 --> 00:00:34.617
watching the fiction.

NOTE Paragraph

00:00:36.324 --> 00:00:37.761
There's nothing wrong with it.

00:00:37.785 --> 00:00:40.634
I love watching movies
and going to the theaters.

00:00:40.658 --> 00:00:43.369
The experiences can be
such emotional experiences.

00:00:43.708 --> 00:00:47.135
The art and craft of emotional
experiences within a frame

00:00:47.159 --> 00:00:50.054
can be so strong
to drive a stronger emotion.

00:00:51.178 --> 00:00:53.534
The question we're asking is,

00:00:53.558 --> 00:00:57.511
How the experience of motion pictures
can exist beyond the flat screen.

00:00:58.544 --> 00:01:00.407
How can we start creating content

00:01:00.431 --> 00:01:03.264
for the next generation
of content experiences?

NOTE Paragraph

00:01:04.330 --> 00:01:07.248
Traditionally, when we imagine a scene,

00:01:07.272 --> 00:01:09.446
we look at the frame and the composition.

00:01:10.056 --> 00:01:13.428
We have to think about how we create
depth and parallax

00:01:13.452 --> 00:01:17.857
using foreground, background elements
as the camera moves.

00:01:18.354 --> 00:01:21.965
With the technology today
and devices of VR glasses,

00:01:21.989 --> 00:01:24.785
AR glasses, smart devices,

00:01:24.809 --> 00:01:28.700
allowing three-dimensional
and full navigation in space,

00:01:28.724 --> 00:01:31.220
we have the possibility
to enable audiences

00:01:31.244 --> 00:01:33.954
to experience content
from multiple perspectives.

00:01:34.515 --> 00:01:38.305
What we have to think about
is how we take this technology,

00:01:38.329 --> 00:01:39.897
all the capabilities,

00:01:39.921 --> 00:01:45.301
and enable the experience
to move farther away inside the scene.

00:01:45.325 --> 00:01:49.119
Now we're not talking about video games
or computer-generated actors,

00:01:49.143 --> 00:01:51.912
which look tremendously realistic.

00:01:52.485 --> 00:01:55.365
We're talking about real actors
and real performance,

00:01:55.389 --> 00:01:56.674
performing onstage.

00:01:58.127 --> 00:02:02.104
We have to start thinking
how we capture the actors

00:02:02.128 --> 00:02:04.380
and how we capture the real scene

00:02:04.404 --> 00:02:06.350
in order to immerse inside.

NOTE Paragraph

00:02:06.374 --> 00:02:09.675
Now, we're familiar
with the 360-degree video,

00:02:09.699 --> 00:02:12.215
where you place a camera inside the scene

00:02:12.239 --> 00:02:15.993
and you can create this beautiful
panoramic image all around you,

00:02:16.017 --> 00:02:17.557
but from the same aspect,

00:02:17.581 --> 00:02:19.770
filmmaking is still frontal.

00:02:20.472 --> 00:02:23.259
In order to emerge fully inside the scene,

00:02:23.283 --> 00:02:27.327
we will need to capture the light
from all the possible directions.

00:02:27.351 --> 00:02:32.057
We will have to surround the scene
with an enormous amount of sensors,

00:02:32.081 --> 00:02:35.908
with all possible capabilities
to capture the light

00:02:35.932 --> 00:02:38.464
and enable us to emerge
inside afterwards again.

NOTE Paragraph

00:02:39.908 --> 00:02:41.226
Now, in this setup,

00:02:41.250 --> 00:02:43.774
there's no more foreground or background

00:02:43.798 --> 00:02:45.490
or a camera placed in space

00:02:45.514 --> 00:02:49.031
but hundreds of sensors
capturing the light

00:02:49.055 --> 00:02:51.911
and capturing the motion
from all the possible directions.

00:02:53.021 --> 00:02:55.099
With the new technological advancements,

00:02:55.123 --> 00:02:57.687
we can start looking at 3D photography,

00:02:57.711 --> 00:03:00.558
capturing the light
from multiple perspectives,

00:03:00.582 --> 00:03:02.502
enabling us to reconstruct the object.

00:03:03.534 --> 00:03:05.716
This is like photography in 3D space.

00:03:06.457 --> 00:03:09.132
Now, with these
technological advancements,

00:03:09.156 --> 00:03:12.553
we can record video
not just as a flat image

00:03:12.577 --> 00:03:14.069
but as a volume.

00:03:14.093 --> 00:03:16.989
This is what we call "volumetric video,"

00:03:17.013 --> 00:03:20.608
and it has the capability
to record every action of the scene

00:03:20.632 --> 00:03:22.433
as a full three-dimensional volume.

NOTE Paragraph

00:03:23.138 --> 00:03:25.282
Now, what is a voxel?

00:03:26.193 --> 00:03:29.296
A voxel is like a three-dimensional pixel,

00:03:29.320 --> 00:03:34.616
but instead of being a flat image square,
staying light and colored,

00:03:34.640 --> 00:03:37.901
it's like a three-dimensional
cube in space,

00:03:37.925 --> 00:03:40.328
with x, y, and z positions.

00:03:41.000 --> 00:03:44.810
This enables us to create
a full capture of the scene

00:03:44.834 --> 00:03:46.142
from any perspective.

00:03:46.976 --> 00:03:51.889
Now this renders
a fully light-immersive scene

00:03:51.913 --> 00:03:53.985
from multiple perspectives.

00:03:54.009 --> 00:03:58.929
This capability requires an insane amount
of information to be processed.

00:03:58.953 --> 00:04:03.866
We will have to capture the light
from an enormous amount of cameras

00:04:03.890 --> 00:04:05.405
to create this information.

NOTE Paragraph

00:04:06.573 --> 00:04:09.752
Now, in order to do such a thing,

00:04:09.776 --> 00:04:15.132
we would need a setup that would host
a numerous amount of cameras

00:04:16.051 --> 00:04:18.044
installed in a stage

00:04:18.068 --> 00:04:23.242
and a stage big enough in order to fit
a full cinematic experience.

NOTE Paragraph

00:04:24.099 --> 00:04:28.733
Now that sounds like a crazy idea,
but that's exactly what we did.

00:04:29.583 --> 00:04:31.011
For the last three years,

00:04:31.035 --> 00:04:35.432
we have been building
a huge volumetric camera chamber.

00:04:36.059 --> 00:04:39.210
It's 10,000 square feet of a stage,

00:04:39.234 --> 00:04:42.424
enabling to capture the action
from any location.

00:04:43.184 --> 00:04:45.266
We have deployed hundreds of cameras,

00:04:45.290 --> 00:04:47.806
sending a tremendous amount of information

00:04:47.830 --> 00:04:51.734
to a huge data center
powered by Intel supercomputers.

00:04:52.695 --> 00:04:56.059
The ability to have this 10,000 feet

00:04:56.083 --> 00:04:59.445
enables us to fit any kind of action,

00:04:59.469 --> 00:05:00.921
any kind of performance.

00:05:01.443 --> 00:05:04.008
It is the size of an average
Broadway stage.

00:05:05.397 --> 00:05:07.455
We call it Intel Studios,

00:05:07.479 --> 00:05:10.476
and it's the largest volumetric
stage in the world,

00:05:10.500 --> 00:05:14.054
with the objective
of enabling and exploring

00:05:14.078 --> 00:05:17.121
the next generation
of this immersive media filmmaking.

NOTE Paragraph

00:05:18.498 --> 00:05:20.855
Now, to test these ideas,

00:05:21.966 --> 00:05:26.855
we were thinking about what we can do
as the first scene to try it out.

00:05:27.949 --> 00:05:29.472
So we chose the Western scene.

00:05:30.354 --> 00:05:34.929
We brought horses, set designers, dirt,

00:05:34.953 --> 00:05:38.648
everything needed to create
the full scene of a Western.

00:05:38.672 --> 00:05:41.584
But this time, there was no camera inside.

00:05:42.306 --> 00:05:46.219
There was nothing really moving
besides all the cameras

00:05:46.243 --> 00:05:48.111
installed outside.

00:05:48.423 --> 00:05:51.265
The challenge
of the actors was tremendous.

00:05:51.289 --> 00:05:57.049
They have to perform a flawless action
visible from all the directions.

00:05:57.653 --> 00:06:02.170
There's no possibility to hide a punch
or not show the action.

00:06:02.700 --> 00:06:04.962
Everything is captured
and everything is seen.

NOTE Paragraph

00:06:05.703 --> 00:06:09.401
The output of the capture --

00:06:09.425 --> 00:06:10.885
this is our future capture --

00:06:10.909 --> 00:06:13.736
opened our eyes for
the immense capabilities.

00:06:13.760 --> 00:06:17.721
It was like a full 3D scan
of the entire scene.

00:06:17.745 --> 00:06:21.483
We were able to move around
and travel in the space.

00:06:21.507 --> 00:06:22.669
The thing about this,

00:06:22.693 --> 00:06:26.433
it's not anymore about perceiving
the light emitted from a screen

00:06:26.457 --> 00:06:29.062
but now traveling inside the light,

00:06:29.086 --> 00:06:30.785
traveling inside the scene.

00:06:30.809 --> 00:06:33.722
This obviously opens possibilities
for an enormous amount

00:06:33.746 --> 00:06:37.404
of storytelling
and methodologies of creation.

00:06:37.799 --> 00:06:41.178
This is the possibilities
of your personal narrative,

00:06:41.202 --> 00:06:44.030
the possibility of creating
your own story inside,

00:06:44.054 --> 00:06:45.711
or maybe following other stories.

00:06:47.470 --> 00:06:49.962
Let's take a look
at one of the last renders and see.

NOTE Paragraph

00:06:49.986 --> 00:06:51.058
(Music)

NOTE Paragraph

00:06:51.082 --> 00:06:54.145
What you're seeing here
is full volumetric video,

00:06:54.169 --> 00:06:56.391
and there's no physical
camera in the scene.

NOTE Paragraph

00:06:56.415 --> 00:06:58.328
(Music)

NOTE Paragraph

00:06:58.352 --> 00:06:59.891
We have the full control

NOTE Paragraph

00:06:59.915 --> 00:07:01.490
(Music, sounds of combat)

NOTE Paragraph

00:07:01.514 --> 00:07:03.312
of space and time.

NOTE Paragraph

00:07:03.336 --> 00:07:10.336
(Music, sounds of combat)

NOTE Paragraph

00:07:14.358 --> 00:07:17.169
Now, again, no physical camera was here.

00:07:17.193 --> 00:07:19.867
Everything was captured surrounding.

NOTE Paragraph

00:07:19.891 --> 00:07:22.042
Now, this is very nice,

00:07:22.066 --> 00:07:26.301
but what if we wanted to see the scene,
maybe, from the eyes of the horse?

00:07:26.676 --> 00:07:29.042
Well, we can do that as well.

NOTE Paragraph

00:07:29.066 --> 00:07:30.462
(Horse galloping)

NOTE Paragraph

00:07:30.486 --> 00:07:33.755
So what you're seeing right now
is the same action,

00:07:33.779 --> 00:07:37.200
but this time, we're watching
exactly from the eyes of the horse.

00:07:37.224 --> 00:07:40.882
The possibilities are, well, unlimited.

NOTE Paragraph

00:07:41.360 --> 00:07:42.361
(Applause)

NOTE Paragraph

00:07:42.385 --> 00:07:43.544
Thank you.

NOTE Paragraph

00:07:43.568 --> 00:07:46.975
(Applause)

NOTE Paragraph

00:07:46.999 --> 00:07:51.086
So this is all great
for creators and storytellers.

00:07:51.110 --> 00:07:53.122
It really opens a huge canvas

00:07:53.146 --> 00:07:56.102
for a different type
of storytelling and moviemaking.

00:07:56.126 --> 00:07:57.621
But what about the audience?

00:07:57.645 --> 00:08:00.221
How can the audience
experience this differently?

00:08:00.838 --> 00:08:02.726
In order to [create] our explorations,

00:08:02.750 --> 00:08:04.566
we partnered with Paramount Pictures

00:08:04.590 --> 00:08:08.641
in order to explore immersive media
in a Hollywood movie production.

00:08:09.109 --> 00:08:11.253
Together with the director Randal Kleiser,

00:08:11.277 --> 00:08:16.085
we reimagined the iconic movie of 1978,

00:08:16.109 --> 00:08:17.460
"Grease."

00:08:17.484 --> 00:08:19.862
Some of you know it, some of you don't.

00:08:19.886 --> 00:08:22.982
A 40-year-old movie, amazing experience.

00:08:23.454 --> 00:08:29.890
And our goal was really to look at how 
we can take this iconic action and dance

00:08:29.914 --> 00:08:32.589
and bring it deeper into the experience,

00:08:32.613 --> 00:08:34.606
bring it deeper into the audience.

00:08:34.630 --> 00:08:37.216
Imagine that you can
not just watch the movie

00:08:37.240 --> 00:08:40.622
but get inside it
and dance with the actors

00:08:40.646 --> 00:08:42.281
and dance with the performance.

00:08:42.305 --> 00:08:48.008
Now we're breaking, really,
the traditional 2D mindset of thinking,

00:08:48.032 --> 00:08:51.305
and bringing a much richer
possibility of moviemaking

00:08:51.329 --> 00:08:52.479
and content creation.

NOTE Paragraph

00:08:53.259 --> 00:08:55.114
But why watch it on the screen?

00:08:56.002 --> 00:08:58.416
Let's try to bring these actors
here on the stage.

00:09:05.165 --> 00:09:07.064
So they're not going to really come --

00:09:07.088 --> 00:09:08.362
I'm going to use an iPad.

NOTE Paragraph

00:09:08.386 --> 00:09:09.387
(Laughter)

NOTE Paragraph

00:09:09.411 --> 00:09:10.562
Sorry.

NOTE Paragraph

00:09:10.586 --> 00:09:15.252
I'm going to use an iPad
in order to bring in augmented reality.

00:09:15.276 --> 00:09:20.109
Now, obviously, these devices
have their own limitations

00:09:21.113 --> 00:09:23.118
in terms of the data-computing process,

00:09:23.142 --> 00:09:25.482
so we have to reduce
the amount of resolution.

00:09:27.016 --> 00:09:30.913
So what I'm doing now,
I'm placing here a marker,

00:09:30.937 --> 00:09:35.777
so I'll be able to position exactly
where I want everyone to appear.

00:09:42.608 --> 00:09:43.759
OK.

00:09:43.783 --> 00:09:45.108
I think we have them here.

NOTE Paragraph

00:09:45.907 --> 00:09:52.304
(Applause)

NOTE Paragraph

00:09:52.328 --> 00:09:53.637
John Travolta, or --

NOTE Paragraph

00:09:53.661 --> 00:09:54.662
(Laughter)

NOTE Paragraph

00:09:54.686 --> 00:09:55.836
a version of him.

00:09:56.776 --> 00:09:58.137
Let's take a look.

NOTE Paragraph

00:09:58.463 --> 00:09:59.614
(Video) Female: Hey.

NOTE Paragraph

00:09:59.638 --> 00:10:01.217
Male: And that is how it's done.

NOTE Paragraph

00:10:01.241 --> 00:10:02.447
Female: Your turn.

NOTE Paragraph

00:10:02.471 --> 00:10:04.031
Male: Hey, guys! Check this out.

NOTE Paragraph

00:10:04.055 --> 00:10:06.985
(Song: "You're the one that I want")

NOTE Paragraph

00:10:07.366 --> 00:10:08.539
Danny: Sandy!

NOTE Paragraph

00:10:08.844 --> 00:10:11.181
Sandy: Tell me about it, stud.

NOTE Paragraph

00:10:12.031 --> 00:10:15.951
(Singing) I got chills.
They're multiplying

NOTE Paragraph

00:10:16.554 --> 00:10:20.940
And I'm losing control

NOTE Paragraph

00:10:20.964 --> 00:10:25.228
'Cause the power you're supplying

NOTE Paragraph

00:10:25.252 --> 00:10:27.261
It's electrifying!

NOTE Paragraph

00:10:27.261 --> 00:10:28.261
(Video ends)

NOTE Paragraph

00:10:28.261 --> 00:10:33.857
(Applause and cheers)

NOTE Paragraph

00:10:33.881 --> 00:10:35.214
Diego Prilusky: Thank you.

NOTE Paragraph

00:10:35.238 --> 00:10:37.485
(Applause and cheers)

NOTE Paragraph

00:10:37.509 --> 00:10:38.801
So as you can see,

00:10:40.039 --> 00:10:43.961
we can watch and experience content
in the traditional way

00:10:43.985 --> 00:10:45.189
or in an immersive way.

00:10:46.014 --> 00:10:47.926
Really, the possibilities are open.

00:10:48.705 --> 00:10:52.157
We're not trying to change
or replace movies.

00:10:52.760 --> 00:10:54.348
We're enhancing them.

00:10:54.372 --> 00:10:59.189
The technologies enable new possibilities
to start thinking beyond the flat screen.

00:11:00.219 --> 00:11:04.094
We're in immersive and really
exciting times in filmmaking.

00:11:04.465 --> 00:11:06.950
We're at the threshold of a new era.

00:11:06.974 --> 00:11:10.122
We're opening the gates
for new possibilities

00:11:10.146 --> 00:11:11.899
of immersive storytelling,

00:11:13.122 --> 00:11:17.733
and exploration and defining
what immersive media filmmaking means.

00:11:18.868 --> 00:11:21.202
We're really just at the beginning,

00:11:21.226 --> 00:11:23.619
and we invite you all to join us.

NOTE Paragraph

00:11:24.150 --> 00:11:25.301
Thank you.

NOTE Paragraph

00:11:25.325 --> 00:11:30.436
(Applause)