Lex Fridman tests Google Beam
00:00:00.000 | Hey Lex, my name is Andrew. I lead the Google Beam team and we're going to be
00:00:03.120 | excited to show you a demo. Whoa, okay. Here we are. Okay, this is real already.
00:00:10.920 | Wow. So you can feel the depth of this. Wow. So for people who probably can't
00:00:20.640 | even imagine what this looks like, there's a there's a 3d version. It looks
00:00:24.000 | real. You look real. It looks real to you. It looks like you're coming out of the
00:00:28.320 | screen. So I saw demos of this, but they don't come close to the experience of
00:00:33.300 | this. I think one of the top YouTube comments on one of the demos I saw was
00:00:36.540 | like, why would I want a high definition? I'm trying to turn off the camera, but
00:00:40.380 | this actually is, this feels like the camera has been turned off and we're just
00:00:44.520 | in the same room together. This is really compelling. That's right. I know it's kind
00:00:48.780 | of late in the day too, so I brought you a snack just in case you're a little bit
00:00:51.480 | hungry, but um... So what can you push it farther and it just becomes... Let's try to
00:00:56.640 | float it between rooms. It kind of fades it from my room into your room. And then you see my hand, the depth of my hand.
00:01:01.620 | Of course, yeah. Of course, yeah. It feels like you've tried this. Try to give me a high five and there's almost a sensation
00:01:06.600 | of feeling touch. Yeah. Almost feel. Yes. Because you're so attuned to, you know, that should be a high five. It feeling like you could connect with somebody that way. So it's kind of a magical experience.
00:01:13.600 | Oh, this is really nice. How much does it cost?
00:01:18.580 | There's nothing. I'm not wearing anything. Well, I'm wearing a suit and tie to clarify. I am wearing clothes. This is not CGI.
00:01:27.560 | There's two things. Two really hard things that we put together. One is an AI video model. So there's a set of cameras. You asked kind of about those earlier. There's six color cameras, just like webcams that we have today.
00:01:39.560 | taking video streams and feeding them into our AI model and turning that into a 3D video of you and I. It's effectively a light field. So it's kind of an interactive 3D video that you can see from any perspective.
00:01:50.240 | That's transmitted over to the second thing, and that's a light field display. And it's happening bi-directionally. I see you and you see me both in our light field displays.
00:01:58.600 | These are effectively flat televisions or flat displays, but they have the sense of dimensionality, depth, size is correct.
00:02:07.820 | You can see shadows and lighting are correct, and everything's correct from your vantage point. So if you move around ever so slightly and I hold still, you see a different perspective here.
00:02:17.520 | You see kind of things that were occluded become reveal. You see shadows that, you know, move in the way they should move.
00:02:22.580 | All of that's computed and generated using our AI video model for you. It's based on your eye position. Where does the right scene need to be placed in this light field display?
00:02:32.300 | I agree just to feel present.
00:02:33.800 | It's real time, no latency. I'm not seeing latency. You weren't freezing up at all.
00:02:37.320 | No, no, I hope not. I think it's you and I together, real time. That's what you need for real communication.
00:02:42.580 | And at a quality level, that I think is...
00:02:44.700 | This is awesome.
00:02:45.380 | This is awesome.
00:02:45.820 | This is awesome.
00:02:45.880 | This is awesome.
00:02:46.000 | Transcription by CastingWords