@nightmakerrecords No, on the contrary, he's very insightful. Check the comment he made a year ago about Project Natal, and compare to our Kinect videos to see how right he was.
@p4tr1ck77 I imagine a recording of a someone passed on, and then sitting in the same room with them, as they talk to you. Maybe not a conversation, but the idea is still pretty awesome.
48, to be precise; twelve independent clusters of four cameras each. Each cluster reconstructs a 3D facade. To see what it looks like with only two camera clusters, check out the other video ("Collaborative Visualization with Tele-Immersion").
Wouldn't motion capture+3D scanning/texturing (beforehand) produce better results than these? Ultimately it's bound to be less realistic than a theoretical perfect camera capture, but with all this 3D noise it's not very immersive either. Or would it still be cheaper and less time consuming to invest in many more cameras (100+?) than motion capture+3D..?
Motion capture also has the advantage of enabling people to be different things than what they really are of course. Like in second life.
Yes, absolutely. There is a very impressive method developed at a Max Planck Institute in Germany (google "Christian Theobalt") that does just that, and gives much better results.
However, it needs very carefully pre-made models (and it's not real-time yet, either). The fundamental benefit of the method shown here is that any random person (or animal) can just walk into the capture space, and will show up on the other side immediately. It's more like a public phone booth in that way.
Oh, ok. :) Keep working on it, it's the future...
And when you say that "it's not real-time yet" are you referring just to the modeling or does also the motion capturing require time to process?
...
I just noticed a paper by Theobalt et al. from 2005 where they "present a self-calibrating framework for optical motion capture, enabling the reconstruction and tracking of arbitrary articulated objects in real-time". You mean there are still problems with real-time motion capture of humans?
Ow alright. I think I just found the "very impressive method" you're talking about; "Performance Capture from Sparse Multi-view Video". It's very impressive indeed, especially since it's done just with 8 cameras. And I can understand how it's not suitable for real-time, yet. I was imagining a lower quality motion capture and a less detailed model/texture when I made the above comments. :)
That's the one. Christian presented the method to my group a few months back, and I wanted to start using it immediately, but unfortunately he told me then that it took quite a bit of processing between capture and playback. So I shelved that idea for the time being. :(
The glasses are still necessary to create the 3D illusion for the viewer. Sorry to hear about your bad experience, but you should try again some time. This is not your old VR. Our users sometimes use the CAVE for hours at a time, and I haven't gotten complaints about headaches or anything yet.
The best part was when he started rotating them around as if they were just 3d models, but looks cooler because they look like real people and your rotating them around with the graceful flow of a 3d interface. Noice!!
Sort of. The people were captured by an array of cameras, and the resulting 3D data is displayed in an immersive environment (the CAVE). All images are projected onto the CAVE's walls and floor, but to a user (or, in this video, the camera) they appear to be standing or walking in space like holograms.
I (Amber Steele, Mills Dancer) got to dance in the tele-immersion space at UCB CITRUS Lab all spring; we were dying to see this next step occur! It looks fantastic! I'm going to cite this in my thesis; but if you need dancers again, I would love to return!
@sadunkal your a fucking dickehead.
nightmakerrecords 1 year ago
@nightmakerrecords No, on the contrary, he's very insightful. Check the comment he made a year ago about Project Natal, and compare to our Kinect videos to see how right he was.
spelunkerucd 1 year ago
This is amazing, just think of the possibilities.
Talking to your son whos halfway around the world, and hes right infront of you.
Think of the video gaming experiences.
Awesome for education....show your students exactly what you are talking about, like its right in front of them
I love technology...
p4tr1ck77 1 year ago
@p4tr1ck77 I imagine a recording of a someone passed on, and then sitting in the same room with them, as they talk to you. Maybe not a conversation, but the idea is still pretty awesome.
pigsareit 1 year ago
is it fake ?
Outsider0210 2 years ago
i assume the dancin women were recorded with 50+ surrounding cameras right?
warlockboyburns 2 years ago
48, to be precise; twelve independent clusters of four cameras each. Each cluster reconstructs a 3D facade. To see what it looks like with only two camera clusters, check out the other video ("Collaborative Visualization with Tele-Immersion").
spelunkerucd 2 years ago
Wouldn't motion capture+3D scanning/texturing (beforehand) produce better results than these? Ultimately it's bound to be less realistic than a theoretical perfect camera capture, but with all this 3D noise it's not very immersive either. Or would it still be cheaper and less time consuming to invest in many more cameras (100+?) than motion capture+3D..?
Motion capture also has the advantage of enabling people to be different things than what they really are of course. Like in second life.
sadunkal 2 years ago
Yes, absolutely. There is a very impressive method developed at a Max Planck Institute in Germany (google "Christian Theobalt") that does just that, and gives much better results.
However, it needs very carefully pre-made models (and it's not real-time yet, either). The fundamental benefit of the method shown here is that any random person (or animal) can just walk into the capture space, and will show up on the other side immediately. It's more like a public phone booth in that way.
spelunkerucd 2 years ago
Oh, and guess what? We're working on motion-captured avatars right now, for exactly the reasons you state. Keep looking.
spelunkerucd 2 years ago
Oh, ok. :) Keep working on it, it's the future...
And when you say that "it's not real-time yet" are you referring just to the modeling or does also the motion capturing require time to process?
...
I just noticed a paper by Theobalt et al. from 2005 where they "present a self-calibrating framework for optical motion capture, enabling the reconstruction and tracking of arbitrary articulated objects in real-time". You mean there are still problems with real-time motion capture of humans?
sadunkal 2 years ago
Sorry the paper is only cited by Theobalt, not authored by. It's actually from Aachen University, by Hornung and Sar-Dessai.
sadunkal 2 years ago
Ow alright. I think I just found the "very impressive method" you're talking about; "Performance Capture from Sparse Multi-view Video". It's very impressive indeed, especially since it's done just with 8 cameras. And I can understand how it's not suitable for real-time, yet. I was imagining a lower quality motion capture and a less detailed model/texture when I made the above comments. :)
sadunkal 2 years ago
That's the one. Christian presented the method to my group a few months back, and I wanted to start using it immediately, but unfortunately he told me then that it took quite a bit of processing between capture and playback. So I shelved that idea for the time being. :(
spelunkerucd 2 years ago
Maybe all you need is an Xbox360. Check out "Project Natal"... It surprised me. It's not yet exactly clear how precise it is though.
sadunkal 2 years ago
you can look but you can't touch
warlockboyburns 2 years ago
how da heck
azariahsimon 3 years ago
that is SO cool! (and kinda creepy too) :) I keep expecting Princess Leia to pop up :)
brandon9271 3 years ago
Princess Leia? No. This is imperial technology!
spelunkerucd 3 years ago
This is the future folks
Boeing727223 3 years ago
Why he wear the glasses? LOL
They guy will have a great headache after that (I have tried) :P
Nice video, BTW.
ilmale 3 years ago
The glasses are still necessary to create the 3D illusion for the viewer. Sorry to hear about your bad experience, but you should try again some time. This is not your old VR. Our users sometimes use the CAVE for hours at a time, and I haven't gotten complaints about headaches or anything yet.
spelunkerucd 3 years ago
What do you use, shutter-glasses or polarized filters?
crim3cost 3 years ago
These are shutter glasses. They work better than polarizing ones, especially with an enclosed multi-screen setup like this.
spelunkerucd 3 years ago
i wonder what it takes to render something like that?
Shane9enahS 3 years ago
The best part was when he started rotating them around as if they were just 3d models, but looks cooler because they look like real people and your rotating them around with the graceful flow of a 3d interface. Noice!!
-JQob
JQob 4 years ago
Dali would have loved this
yarloo 4 years ago
Absolutely excellent. This is the future.
Xhosa4 4 years ago
OMG! this is the best! omg try to get a contract with nintendo or something and make a mmorpg that can do this!
cicilovesfeb 4 years ago
Oh i get it, it's like a virtual Area.
zuriku 4 years ago
its like a star trek hollowdeck
blakeyboy450 4 years ago
Are they holographs?
xXKariBananaXx 4 years ago
Sort of. The people were captured by an array of cameras, and the resulting 3D data is displayed in an immersive environment (the CAVE). All images are projected onto the CAVE's walls and floor, but to a user (or, in this video, the camera) they appear to be standing or walking in space like holograms.
spelunkerucd 4 years ago
I (Amber Steele, Mills Dancer) got to dance in the tele-immersion space at UCB CITRUS Lab all spring; we were dying to see this next step occur! It looks fantastic! I'm going to cite this in my thesis; but if you need dancers again, I would love to return!
QueenZombie 4 years ago
whoa, that looks pretty creepy actually
JonAnta 4 years ago