Wow, will be great to make recordings of people that you can sit and watch long after they're deceased. Maybe with some deep fakery even create AI versions that can respond to conversation.
Project Starline: Feel like you're there, together
211–220 of 539 posts
Re: Project Starline: Feel like you're there, together
#212A good friend of mine at Google is the technical lead of this project (he has a Phd Princeton, and was a professor before joining Google). I've tried it in person and it was truly amazing. They used some very fancy tech when I saw the demo, so I'm thrilled it is finally being announced and possibly shared with a larger audience. Explanation of why it is amazing: It totally fools your perception. No glasses or goggles…
I have wondered in the past if a similar result could be achieved using a 3d headset with some tracking/cameras and removing the headset from the view through a real-time deep fake that could be achieved through a short scan before the call. Would this even be feasible?
Re: Project Starline: Feel like you're there, together
#213https://en.wikipedia.org/wiki/Autostereoscopy
Which type of autostereoscopy is it?
Re: Project Starline: Feel like you're there, together
#214Make an entire wall out of this, now you are virtually colocated.
Re: Project Starline: Feel like you're there, together
#215Earlier quoted context omitted.
NO WAY. It is impossible for me to explain how/why it works so well.
I am sure that the immersion of the experience is higher. My question (and perhaps that of GP) is: is this greater immersion actually beneficial to communication? I think this is cool tech, and valuable. I'm just not sure that it offers a communication benefit over well-lit, well-miced, wired, low latency, 8K videoconferencing. Maybe there's some 3D emotional perception face processing stuff that we have deep in our…
I think you might be underestimating the value of viewing a 3D model on a no-glasses 3D display. This is one of the basic aspects of in-person communication we take for granted that current 2D technology can't replicate. You can move your head and actually see a different angle of the person in front of you. This can even be subtle, our brain will still pick up the effect, and it makes the experience beyond what we usually consider as "immersive".
Yes, having low latencies and high definition video is an important aspect of this, but the 3D part is no gimmick. Once the technology improves and gets affordable this is a game changer for how we communicate online. The step after that are holographic displays, and since we'd be used to 3D models and smart displays, it probably won't feel like such a big jump.
I'm _super_ excited about this project. Hopefully Google doesn't axe it. (:
Re: Project Starline: Feel like you're there, together
#216The biggest barrier to virtual healthcare today is that patients find it hard to connect with and trust doctors over a screen. This seems like a perfect product fit, especially among older people.
Is there evidence of this? This is not what I would guess the greatest barrier is to virtual healthcare
Re: Project Starline: Feel like you're there, together
#217My first thought: in 2030 when I’m calling grandma with this, I will first need to accept cookies, then accept the new Google privacy policy, then sign in to my Google account, then watch 2 20-second long pre roll ads.
We're witnessing magical tech and innovation, and here we are back to making fun of signing in, ads and cynicism about Google shutting down projects.
Especially because most of Google's productivity apps don't even have ads. I think it's just Gmail on mobile at the moment.
Re: Project Starline: Feel like you're there, together
#218Earlier quoted context omitted.
Penicillin. But then, he wasn't trying to make money off of it. And basically anything Nintendo pushes as a console gimmick. It's not that the tech immediately goes from research to broadly accessible, but rather that they tend to take old tech that no one saw as having profitable consumer applications and find one for it. In that way, as far as consumers are concerned, it goes from unknown to widely-used without mak…
Penicillin, maybe? But I wonder how quickly it became readily available outside of the Western world. And I see that Nintendo has apparently sold an extremely impressive number of consoles ( https://www.nintendolife.com/news/2019/11/nintendo_has_now_s... ). But even if everyone only bought one console each, that's only about 10% of world population. This may be a little unfair, but I do wonder if there isn't a tenden…
To say that a single company's products being used by even a single digit percentage of the world population doesn't meet the requirements to ve considered "widely available" is a stretch.
In any case, you said "important," not "widely available," and yes, Nintendo's products are hugely important. Many of today's technological advancements can be traced back to their proving that a given use case for a primitive version of a given technology was viable.
Re: Project Starline: Feel like you're there, together
#219Earlier quoted context omitted.
I doubt you need gigabit for an 8K stream. The real issue is the abysmal common network infrastructure. Latency will be a bottleneck if most ISPs don't care about treating your packets properly.
Agreed, 10Mbps is likely where it'll be, probably less. If I were to guess, they are going to apply a lot of smarts to texture mapping to avoid needing a lot of bandwidth.
Doubtful, IMO. The fact that you need it to be both extremely low latency and with essentially zero compression artifacts (probably lossless, based on their goal). If the numbers listed here[1] are correct, then the most efficient lossy codec at that time was doing 100 minutes of 8k video in ~37GB of data. From that we can intuit that it was using an average of 50 Mbps for that 100 minutes of video. For the most efficient codec, and I'm not even sure from that whether it was using lossy or lossless numbers, because apparently HVEC can do both (but I would assume lossy, since it's about streaming video in that case).
You can't do weird texture mapping or lossy compression and expect people to really seem like they are there. Even if you don't notice that stuff normally watching a video, I think you'll notice it when you're interacting like someone is really in front of you, and that will throw off the immersion.
1: https://www.quora.com/In-regards-to-filesize-how-big-is-1-mi...
Re: Project Starline: Feel like you're there, together
#220HP did this at least 15 years ago with their "Halo" conferencing systems: https://www.networkworld.com/article/2258553/inside-the-halo... https://www.youtube.com/watch?v=TC4sNztp8dk
HP's Halo conferencing system had several studio quality cameras that would change the video feed based on who was talking. There were also specially placed mics on the conference table to keep audio crisp. The video quality was impressive, however you had the same issues that you have with current web-cam based systems. Eye-contact was non-existent. While the camera placement was above the middle-top of the LCD scre…
> Eye-contact was non-existent.
Potentially a solved problem, just fix it in post. :)
https://www.zdnet.com/article/windows-10-microsoft-finally-l...
I wonder how well it works, and how much latency (if any) it adds to the feed.
I'm also sad it isn't rolled out more generally, a very strange feature to lock behind a small-ish volume hardware product.