next Elderscrolls Game wont have boring Caves anymore. Bethesda People will just run around in real Caves and Scan them. "The Caves in this Game look so realistic!".
Or maybe not, since we have yet to learn quite a lot of how the Machine "sees" our World.
this will have huge impact on the industry. now with this you could reconstruct 3D shapes with 1 mm accuracy. imagine an upgraded version where it will have a higher resolution with 1 µm tolerance. and all this at a fraction of cost compared to modern laser scanning approach.
it would be already useful to reconstruct complete buildings.
I can see that this tech can be very useful for driverless cars. Currently driverless cars like Google's use expensive laser to sense the surrounding environment. This will greatly reduce the cost and complexity of sensing systems and bring driverless quicker to market.
As soon as you'll put a glass on it and as soon as this glass will be properly tracked I might be slightly impressed. The method does not work with any shiny material aswell. lame.
@bireno: approximate 3d models can be used as a starting point for 3d modelers. The geometry can be edited using 3ds max or other 3d software to adjust the number of polygons (increase OR decrease resolution).
@bireno: approximate 3d models can be used as a starting point for 3d modelers. The geometry can be edited using 3ds max or other 3d software to adjust the number of polygons (increase OR decrease resolution).
The future: Put on some virtual reality glasses, connect them to your smartphone, play augmented reality multiplayer shooters with your friends. Imagine playing Left for Dead in your own house, actually running around with guns that appear to shoot real bullets. Fuck keyboard + mouse.
Or how about dining with your friend who is on the other side of the world? His 3d model appears in your vision, you can hear and see him.
Or playing card games that actually come to life?
I think people are missing the point of this kind of work. It's not meant to be a replacement to 3d modelers, it's a break-through in how computers make sense of OUR environment. With known surfaces, walls, objects, etc...we can start to extend the computer interface beyond the mouse & keyboard and into a new world of computer vision where we can detect the movement, position and rotation of any arbitrary object, turn surfaces into an input devices and finally get away from our desks and chairs.
@cruxphotography , I agree with you that this is no replacement for 3D modelers. But it can help designers/artists/engineers model real objects much faster and more accurately. Imagine if I want to place a car in a game I am designing. Instead of designing the car from scratch, I can scan a model of my toy car and import into the game in no time. That amounts to saving 2 to 3 hrs for modelling a car.
Modellers are coming at this from the wrong direction. Imagine if this was your only tool for creating game content. What sot of game could you make? What sort of content would be usable? Bear in mind this is just an experiment with generic hardware. How will the next generation of games console handle this? Right now, gaming is basically a specialization of animation. This is one way to bring photography back into games. It may be crude and fuzzy but its real and people respond to that.
Actually they wont' at least for some time. Scan an object that does not exist. Creating a physical model to just scan it would be too cost intensive.
Additionally for now (at least for now) the resolution is low. Even when it increases, some one will have to clean up the mesh as the density might be too much.
Finally, they said the same thing about motion capture. Yet the need for animators has simply been growing and growing.
"KinectFusion is a team effort between Microsoft Research Cambridge, Imperial College London, Newcastle University, Lancaster University, and the University of Toronto. "
Probably closed source, but please prove me wrong!
The "Lazy Susan" would then have to be re-named the "Lazy 3D Modeller" due to how lazy that would be... you know, just rotating a plinth. You get it? I'll get my coat.
Hey, this seems like a pretty easy and fast way to scan 3D point clouds... And supposedly "Unlimited Detail" can render unlimited point cloud data. Join these two and we will have the next-gen ultra-realistic graphics.
@denilsonsa Data takes space; point cloud data takes huge freaking gobs of space. If you are content with a small number of models repeated infinitely you can render "inifinite" point-cloud data. If you want a real game; something you'd actually want to play rather than a tech demo, you'd want at least to have some sort of hybrid approach that uses polygon models for animated objects, which point clouds don't deal well with at all.
@abram730 Like hell. A typical machine has perhaps 512 MB to 2 GB of graphics memory, 4 to 16 GB of RAM memory and the bandwidth limitations of PCI-E will prevent you from shoveling several gigabytes over to the graphics card every frame. An SSD can read a few hundred megabytes per second under ideal circumstances, that's pitiful. You can't ship multi-terabyte games to consumers.
I'm presuming this is outputting a voxel system rather than mesh geometry. Then perhaps there's some auto-cleaning to select the best 'surface' voxels', hence optimised speed. beyond that, it's possible to consider building a mesh, but I don't know whether that's been made feasible in real-time here?
FYI: This isn't going to do much for 3d modelers. The model geometry isn't going to be efficient enough. Basically, models for games are carefully created with a polygon budget in mind, detail where it needs to be, less where it doesn't. Proper modeling on joint areas for animation, etc.. While awesome, this software isn't going to really help streamline games aside from offering something to 'trace' in 3d with a more efficient mesh.
I dont see why you couldn't retopologize any of the objects captured with the Kinect easily. There are plenty of professionals in the industry using sculpting software to make and edit high poly models with poor/temporary topology (similar to the output in this video), then retopologize them for animation and poly budget later.
@Bireno This could do a ton for modelers - any model in there could either be retopolized by hand or by software (FYI Modern automatic retopology/polyreduction software lets you interact with how and where details is reduced) But as you say for tracing; The kinect model could easily be used to transfer a perfect RGB/diffuse and normal map to an optimized object/UV.
This could all greatly help modelers, it just wouldn't be very suitable for anything not realistic though.
@Bireno I do think it would be extremely usefull for people compositing 3d in liveaction. Less rotoscoping work. And it would be perfect reference scene for 3D animators.
@Bireno FYI: 3D modelers often use incredibly high-poly models to create normal maps, which do not affect the poly count (the polys come from the underlying model that is actually used and then normal-mapped). ZBrush is a common tool for creating these high-poly models, but this (I assume) may give yet another alternative. Just a FYI for your FYI.
I have to say that the most impressive part was when they took the tea jar away and the modeled one remained in the real-life footage. That was mind blowing!
This is HUGE; my best congratulations to this team; This is amazing technology
I would think there would have been actual 3d animators watching this and posting comments, but I don't think anyone here sees the mess they would have to clean up if given the raw output. It would probably be the same amount of work if not more work then doing it from scratch. The advantage, is with the amount of work input, you have the potential for far greater output because the broad strokes are done. This is a BIG win for 3d modelers, and an outstanding tech and intellectual achievement.
@InuvikPhil google already does a simple parallax depth matching with their streetview data.. you can see how the wall-facing links match up with real world buildings/trees
Watching the part with 3d objects w/ physics superimposed onto the real world made me think of only one thing: 3d zombie survival FPS in my own neighborhood....
SOmeone wiht a makerbot use this to do a high res scan of their own face and print a copy of themselves. No it hasn't been done. It's sucked in the past. No detail at all.
This is seriously just a miniaturization step away from high quality augmented reality. Build a kinect into a pair of eyeglasses with a HUD and hook it up to a phone with a badass GPU and watch the world come to life.
Make this technology work with video glasses that have a camera. Then wherever you're looking is scanned and recreated digitally. CG characters could be added that move through the environment similarly to the particle ball effect. You'd be looking at live video of your house but suddenly a cg girl appears that you can see interacting with the real environment and your "multi touch". : P
This is really impressive tech and a big step forward for virtual reality.
@GreatVomitto i thought it was clear by firing particles into the scene... you can constantly be bombarding the actresses with various fluid simulations throughout the duration of the movie.
i see future video cameras having this sort of thing embedded so visFX guys can add 3d effects really easily.
Olirap 1 day ago
It's been six months. Release it you lazy turds.
Feuyaer 2 weeks ago in playlist Favorite videos
@Feuyaer the open source one has already been released, running it is just somewhat of a pain right now but it works.
matadorqk 4 days ago
Comment removed
abram730 3 weeks ago
Comment removed
abram730 4 weeks ago
This could do wonders to autonomous vehicles in terms of anticipating dangers or at least warning systems for human drivers.
(Oh, and of course this is one step closer to that construction interface Tony Stark has in his tinker cellar :) )
RevFilmore 1 month ago
next Elderscrolls Game wont have boring Caves anymore. Bethesda People will just run around in real Caves and Scan them. "The Caves in this Game look so realistic!".
Or maybe not, since we have yet to learn quite a lot of how the Machine "sees" our World.
madman123456 1 month ago
source code? XD
CeAsena 2 months ago
this will have huge impact on the industry. now with this you could reconstruct 3D shapes with 1 mm accuracy. imagine an upgraded version where it will have a higher resolution with 1 µm tolerance. and all this at a fraction of cost compared to modern laser scanning approach.
it would be already useful to reconstruct complete buildings.
well, take all my money.
ChuckVanDamme 2 months ago
omfg is there possible to make reconstruction of my home and put it into gta ?
MsBrumak 3 months ago
Think of this for crime-scene reconstruction / investigation.
shangomatic 3 months ago 2
Reminds me of playing rainbow six veagas
Tm0g762 3 months ago
Awesome!
hanlong85 4 months ago
exciting :D
its really getting there..
now we just need to learn how to apply this in many interesting ways
iisthphir 4 months ago
Two words.
Mind. Blown.
agentEE7 4 months ago
Other than a kinect, what do you need to do this? I'd LOVE to reconstruct my environment in a similar way!
Tikvanaya 4 months ago
fake! uhm... wait a minute. uh... i think this is not so easy to fake. actually the technology to fake it is still missing xD
boogie0815 4 months ago
Wow, I laughed at the augemented reality joke apps but this video is just scary lol.
Gz to you guys.
bernatk 4 months ago
How long does it take until we get the software to make use of the KinectBar for 3D-scanning dear KinectFusion-Team?
DelphiDelphin 4 months ago
amazing!
Wulfiewolf 4 months ago
I can see that this tech can be very useful for driverless cars. Currently driverless cars like Google's use expensive laser to sense the surrounding environment. This will greatly reduce the cost and complexity of sensing systems and bring driverless quicker to market.
nelsonstx 4 months ago 2
OH THE things I could do with that gadget! gimme gimme gimme!
masseyHHVP 4 months ago
imagine: scanning of an entire city with kinect only! fly through them, in real 3D. amazing!
kadeer 4 months ago
Will they release the project as Open-Source at some point?
snaileri 4 months ago 5
What happends if you try to reconstruct a mirror or a bathtub of water?
What about reconstruction a cloud of smoke?
jonsku9393 5 months ago in playlist Käyttäjän jonsku9393 suosikkivideot 2
And people want to say the Sony Move is just like the Kinect, hahahahahah!
sw204me 5 months ago 2
As soon as you'll put a glass on it and as soon as this glass will be properly tracked I might be slightly impressed. The method does not work with any shiny material aswell. lame.
Moratorium 5 months ago
This comment has received too many negative votes show
USELESS
sikisikiamimis 5 months ago
@bireno: approximate 3d models can be used as a starting point for 3d modelers. The geometry can be edited using 3ds max or other 3d software to adjust the number of polygons (increase OR decrease resolution).
andrelcaron 6 months ago 4
@bireno: approximate 3d models can be used as a starting point for 3d modelers. The geometry can be edited using 3ds max or other 3d software to adjust the number of polygons (increase OR decrease resolution).
andrelcaron 6 months ago
The future: Put on some virtual reality glasses, connect them to your smartphone, play augmented reality multiplayer shooters with your friends. Imagine playing Left for Dead in your own house, actually running around with guns that appear to shoot real bullets. Fuck keyboard + mouse.
Or how about dining with your friend who is on the other side of the world? His 3d model appears in your vision, you can hear and see him.
Or playing card games that actually come to life?
Bionuker 6 months ago 6
quite nice. does the kinect 3D work in sunlight?
DanFrederiksen 6 months ago
I think people are missing the point of this kind of work. It's not meant to be a replacement to 3d modelers, it's a break-through in how computers make sense of OUR environment. With known surfaces, walls, objects, etc...we can start to extend the computer interface beyond the mouse & keyboard and into a new world of computer vision where we can detect the movement, position and rotation of any arbitrary object, turn surfaces into an input devices and finally get away from our desks and chairs.
cruxphotography 6 months ago 77
@cruxphotography , I agree with you that this is no replacement for 3D modelers. But it can help designers/artists/engineers model real objects much faster and more accurately. Imagine if I want to place a car in a game I am designing. Instead of designing the car from scratch, I can scan a model of my toy car and import into the game in no time. That amounts to saving 2 to 3 hrs for modelling a car.
cskvarma6 2 months ago
Comment removed
cruxphotography 6 months ago
Comment removed
cruxphotography 6 months ago
Impressive. o.o
KamatsuKyoto 6 months ago
Amazing
downard21 6 months ago
6 Persons got no FL Player.....
PHILXFROMBHK 6 months ago
could one make a file from this to pipe into a 3d printer?
i would love a miniature of my room
P8ntBal1551 6 months ago
this is exiting! i wonder, when the book and lid was moved 3D reconstr updated but didn't show the movement. is it something that can be solved?
vroomik 6 months ago
Modellers are coming at this from the wrong direction. Imagine if this was your only tool for creating game content. What sot of game could you make? What sort of content would be usable? Bear in mind this is just an experiment with generic hardware. How will the next generation of games console handle this? Right now, gaming is basically a specialization of animation. This is one way to bring photography back into games. It may be crude and fuzzy but its real and people respond to that.
DorkingtonHacker 6 months ago
Comment removed
abram730 4 weeks ago
Are those textures added manually or does it somehow add them automatically using the RGB image?
Jujukoira 6 months ago 3
this shows how much the kinect can do.
and NO game developer anywhere has a clue what to do with it <_<
veyron92 6 months ago 4
insanely cool :)
liqube 6 months ago
Comment removed
DWTDmitri 6 months ago
Release that thing already! :D
JanHofmeister 6 months ago
just stunning
JASONE1986 6 months ago
Some inovative stuff! You can shoot 3D movies pretty fast with this, or shoot in 3D cheaper. Or maybe not..
volosblur 6 months ago
this will change the games and de internet chating...
alguemvj 6 months ago
This is great
haoala 6 months ago
That real time colouring is the coolest thing ever. Physics in 3D camera mapped area also amaze me.
These talented guys should be working for Microsoft.
RealationGames 6 months ago
@RealationGames But they are.
XantheFIN 6 months ago
@XantheFIN
Oh, I seemed to miss the opening intro.
RealationGames 6 months ago
This is not technology, its magic :-o
datee74 6 months ago
This is awesome, you've reached a real turning point here ! Great job and wish you the best
Benyaminu 6 months ago
This is better than porn.
guxit 6 months ago 66
@guxit But I am sure people will apply this to porn. The result is -- much better porn.
blower05 4 months ago 6
What kind of worthless sack of sub-human garbage clicks dislike on a video this cool? I think some people just click dislike on things to be dicks.
ibender 6 months ago
Will there be an SDK to utilize this technology?
tgraupmann 6 months ago
Comment removed
tgraupmann 6 months ago
Is this scene generation and physics being done real-time or is the input saved and we are looking at something preprocess?
Castaa 6 months ago
@Castaa Realtime of course
vibinjk 6 months ago
Godlike!!!
DonnyThailand 6 months ago
Modllers will lose their jobs or in other words we can their work has become reduced.Kindly update in other divisions of 3d guys
hari92dp 6 months ago
@hari92dp
Actually they wont' at least for some time. Scan an object that does not exist. Creating a physical model to just scan it would be too cost intensive.
Additionally for now (at least for now) the resolution is low. Even when it increases, some one will have to clean up the mesh as the density might be too much.
Finally, they said the same thing about motion capture. Yet the need for animators has simply been growing and growing.
prodeous 6 months ago
Comment removed
abram730 4 weeks ago
Incredible! Congrats
cerlendson 6 months ago
maybe the kinect will actually recognize you properly now. BAM! there it is.
Nazareadain 6 months ago
Aerosmith did this in 1994, come on, get with the times MS..... watch?v=zSmOvYzSeaQ)
elmalakai75 6 months ago
Is there code available? Where are you guys working at?
paulclayvideos 6 months ago
@paulclayvideos Answered my own question:
"KinectFusion is a team effort between Microsoft Research Cambridge, Imperial College London, Newcastle University, Lancaster University, and the University of Toronto. "
Probably closed source, but please prove me wrong!
paulclayvideos 6 months ago
Hey guys Im a 1 HANDED IRISH GAMER who plays xbox
Please show us some support :D
3HandGaming 6 months ago
7:40 now point with your finger to where the digital man touched you little girl.
kiyotewolf 6 months ago
Google Maps is Gonna Get Fucked, Bing is Gonna use this for their Maps
theend1245 6 months ago
@theend1245 what is your point now? for over 2000 years maps have been flat, why would you need a 100000000000 terrabite map of the world?
tycho5555555 6 months ago
@tycho5555555 DOnt ask me, ask Google
theend1245 6 months ago
it's a scanner 3D.
Can you export the result?
olivierschimpf 6 months ago
The "Lazy Susan" would then have to be re-named the "Lazy 3D Modeller" due to how lazy that would be... you know, just rotating a plinth. You get it? I'll get my coat.
vikingquest1 6 months ago
this is great. Now I can model myself working and go play xbox all day. Kinect FTW!
pavkey88 6 months ago
That's incredible, congratulations!
Lexoka 6 months ago
Mindblowing!
damjanmx 6 months ago
This has porn written all over it.
elinoree 6 months ago
Does anyone know if this software is open to the public like some of the other kinect stuff shown in the past?
crewshin 6 months ago
Hey, this seems like a pretty easy and fast way to scan 3D point clouds... And supposedly "Unlimited Detail" can render unlimited point cloud data. Join these two and we will have the next-gen ultra-realistic graphics.
denilsonsa 6 months ago
@denilsonsa Data takes space; point cloud data takes huge freaking gobs of space. If you are content with a small number of models repeated infinitely you can render "inifinite" point-cloud data. If you want a real game; something you'd actually want to play rather than a tech demo, you'd want at least to have some sort of hybrid approach that uses polygon models for animated objects, which point clouds don't deal well with at all.
soylentgreenb 6 months ago
Comment removed
abram730 4 weeks ago
@abram730 Like hell. A typical machine has perhaps 512 MB to 2 GB of graphics memory, 4 to 16 GB of RAM memory and the bandwidth limitations of PCI-E will prevent you from shoveling several gigabytes over to the graphics card every frame. An SSD can read a few hundred megabytes per second under ideal circumstances, that's pitiful. You can't ship multi-terabyte games to consumers.
soylentgreenb 3 weeks ago
Comment removed
abram730 3 weeks ago
Very impressive.
JonathanFBock 6 months ago
Insane
glacierise 6 months ago
Please, post to vimeo! That's where all the technical directors and researchers lurk!
Matic3d 6 months ago
I have nothing but admiration for the people who coded this. Fucking insane.
DaRkStAr925 6 months ago 2
Comment removed
CresseyC 6 months ago
Very impressed. Look forward to seeing more of this.
darkerbright 6 months ago
Fuckin Win bro
UnbreakableFury1 6 months ago
This comment has received too many negative votes show
wow what a fun of my lifetime! (not)
wtf is the fun of this
wolfkingewan 6 months ago
Im a noob in this stuff.. but..
Cant this be used to create maps in the gaming world? They would be very realistic.
Like those Google streetview cars.
This way you get real life like maps for games. A lot faster to take thousends of pictures and recreate them.
ABurghouts 6 months ago
hi guys, this more of a win for compositors and trackers than modelers.
whoever turns this into a commercially available camera with the outputs that we see in this video, is about to get really really rich.
ustuner3d 6 months ago
I'm presuming this is outputting a voxel system rather than mesh geometry. Then perhaps there's some auto-cleaning to select the best 'surface' voxels', hence optimised speed. beyond that, it's possible to consider building a mesh, but I don't know whether that's been made feasible in real-time here?
sugokuGENKI 6 months ago
In a couple of years, compress this technology into a couple of glasses (and hardware unit, if needed) and you got yourself constant AR!
(Though chances of getting run over by cars that the software didn't properly update while running around town zapping AR aliens = fairly high)
drunkenmuse 6 months ago
next thing for it will be to recognize a kettle-like surface is the kettle and start to interact or animate it…
valentinalexeev 6 months ago
Is it not just doing the front shell? Hence the resulting images not being spun.
brainiacgames 6 months ago
@brainiacgames it models everything it sees. If it never sees the back, then it never models it.
It builds up a 3D image in it's mind as the kinect moves and rotates arbitrarily around the scene, much like your own brain's visual system does.
The technique isn't technically new, it's called "SLAM".
What this video shows is subtle new techniques to improve how SLAM works.
roidroid 6 months ago
this is amazing
yohank2004 6 months ago
FYI: This isn't going to do much for 3d modelers. The model geometry isn't going to be efficient enough. Basically, models for games are carefully created with a polygon budget in mind, detail where it needs to be, less where it doesn't. Proper modeling on joint areas for animation, etc.. While awesome, this software isn't going to really help streamline games aside from offering something to 'trace' in 3d with a more efficient mesh.
Bireno 6 months ago 5
@Bireno Naysayers gonna naysay.
siddkulk 6 months ago
@Bireno
I dont see why you couldn't retopologize any of the objects captured with the Kinect easily. There are plenty of professionals in the industry using sculpting software to make and edit high poly models with poor/temporary topology (similar to the output in this video), then retopologize them for animation and poly budget later.
Torturecap 6 months ago
@Bireno This could do a ton for modelers - any model in there could either be retopolized by hand or by software (FYI Modern automatic retopology/polyreduction software lets you interact with how and where details is reduced) But as you say for tracing; The kinect model could easily be used to transfer a perfect RGB/diffuse and normal map to an optimized object/UV.
This could all greatly help modelers, it just wouldn't be very suitable for anything not realistic though.
drunkenmuse 6 months ago
@Bireno I do think it would be extremely usefull for people compositing 3d in liveaction. Less rotoscoping work. And it would be perfect reference scene for 3D animators.
brutesquefilms 6 months ago
@Bireno FYI: 3D modelers often use incredibly high-poly models to create normal maps, which do not affect the poly count (the polys come from the underlying model that is actually used and then normal-mapped). ZBrush is a common tool for creating these high-poly models, but this (I assume) may give yet another alternative. Just a FYI for your FYI.
nillian86 6 months ago 4
@nillian86 you're fucking dumb
TeHzoAr 6 months ago
@nillian86 (fyi)
TeHzoAr 6 months ago
Its called re-topologizing the mesh, and their are algorithms for that. The artists will just need to clean shit up afterwards...
uriel88 6 months ago
@Bireno It may not be perfect for a final model but it's a great starting off point, especially with fast retopology in apps like 3D-Coat.
philnolan3d 6 months ago
@Bireno it's just a matter of time...
ILCOSTI 5 months ago
Comment removed
Bireno 6 months ago
I have to say that the most impressive part was when they took the tea jar away and the modeled one remained in the real-life footage. That was mind blowing!
This is HUGE; my best congratulations to this team; This is amazing technology
gadget00 6 months ago
I would think there would have been actual 3d animators watching this and posting comments, but I don't think anyone here sees the mess they would have to clean up if given the raw output. It would probably be the same amount of work if not more work then doing it from scratch. The advantage, is with the amount of work input, you have the potential for far greater output because the broad strokes are done. This is a BIG win for 3d modelers, and an outstanding tech and intellectual achievement.
allnorweiganwood 6 months ago
I may need help finding my jaw on the floor after watching this. That is simply amazing.
felekar 6 months ago
This has been flagged as spam show
и ещё помни kinect СЛЕДИТ ЗА ТОБОЙ !!
NOT83RUS 6 months ago
Comment removed
NOT83RUS 6 months ago
сдаётся мне всё же не миновать нам терминаторов и матрицы !
NOT83RUS 6 months ago
Dude how does this work???
cepomwa 6 months ago
i'll be impressed when i see the wire meshes. bet the geometry's a mess.
Robstailey 6 months ago
HOLY FSCKING HELL. THIS IS MINDBLOWING. Where's the download link!?
dpcnull 6 months ago
Yo autodesk, how'd it go with photofly?
Allingby 6 months ago
Holy SHIT is that cool!
Dmon9055 6 months ago
un. fucking. believable.
hellocharlien 6 months ago
that will be cool for blind people
AcmeSeller 6 months ago
@AcmeSeller H3H3H3H3 >:)
roidroid 6 months ago
amazing stuff
champus1969 6 months ago
This is amazing dude! Great work, are you realeasing the source? Or do you have any project page?
niniomigrania 6 months ago
I had a mind organism from watching this
SeriousTyro 6 months ago
Start scanning everything please.
Get a database going of EVERY object in the world.
A boon to game makers. :D :D
wonmeanlee 6 months ago
@wonmeanlee "A boon to game makers. :D :D"
Yeah and I can imagine that this could put a lot of 3D artists out of the job!
Danny77uk 6 months ago
@wonmeanlee this is going to drive Ikea nuts.
All these people running around their stores, holding kinects and laptops.
RELEASE THE OTTOMANS!!
roidroid 6 months ago
This is better than bullshit unlimited detail crap.
KeLopezDOTCL 6 months ago
awesome awesome stuff... the fact that all this stuff is real time... real wow factor...
devothethird1 6 months ago
This has been flagged as spam show
Oh my god....
Kadda67 6 months ago
this is some pretty futuristic stuff
eigentensor 6 months ago
reminds me some of the things that the 3ds could do, but that was only scratching the surface. This is way more in depth
Hippy10000 6 months ago
Dude! The applications for the are endless
PiefaceclownPrdctns 6 months ago
In the future: google Street View gets a modified 3d scanner like this, that is placed on top of a car...
means: driveable world 3d model, videogame style
InuvikPhil 6 months ago 23
@InuvikPhil google already does a simple parallax depth matching with their streetview data.. you can see how the wall-facing links match up with real world buildings/trees
nothing like this, but still.
also, this is only for 5 meters distance
sholio 6 months ago
So real time game rendering could handle all these polys?
triwa18 6 months ago
Perfect tool for filming sets. Is there a chance we can have a copy of this software ?
thanks, you rock !
nitrofcire 6 months ago
Watching the part with 3d objects w/ physics superimposed onto the real world made me think of only one thing: 3d zombie survival FPS in my own neighborhood....
JeffCiesielski 6 months ago
Holy CRAP!
DillonThomasDigital 6 months ago
SOmeone wiht a makerbot use this to do a high res scan of their own face and print a copy of themselves. No it hasn't been done. It's sucked in the past. No detail at all.
cymonsgames 6 months ago
SCAN ALL THE THINGS!
DoctorCapitalist 6 months ago 12
@DoctorCapitalist how do I thumbs-up your comment over 9000?
gvdwatt 6 months ago
This has been flagged as spam show
@gvdwatt What did I say? :S
DoctorCapitalist 6 months ago
3d animators who animate 3d characters also have an easy job now. Very natural animations with human bones can be accomplished with the kinect.
SyntaxBlitz 6 months ago
That's fantastic! :D
Auxon 6 months ago
And yet Microsoft choose to make shitty dancing games, and crappy waggling minigames with it.
MisterTVenables 6 months ago 3
@MisterTVenables Microsoft research in Cambridge is one of the contributors to this project.
Auxon 6 months ago
Awww shit, my professor's working on this.
ArtemissimetrA 6 months ago
This is seriously just a miniaturization step away from high quality augmented reality. Build a kinect into a pair of eyeglasses with a HUD and hook it up to a phone with a badass GPU and watch the world come to life.
Jargonwhat 6 months ago 4
Absoultely awesome :D
SilynJaguar 6 months ago
So how porn industry will benefit from this?
GreatVomitto 6 months ago 158
@GreatVomitto 3:48 for interactive money shot
incarnedine 6 months ago
Comment removed
LostInTheAbsurd 6 months ago
@GreatVomitto
Make this technology work with video glasses that have a camera. Then wherever you're looking is scanned and recreated digitally. CG characters could be added that move through the environment similarly to the particle ball effect. You'd be looking at live video of your house but suddenly a cg girl appears that you can see interacting with the real environment and your "multi touch". : P
This is really impressive tech and a big step forward for virtual reality.
LostInTheAbsurd 6 months ago
@GreatVomitto i thought it was clear by firing particles into the scene... you can constantly be bombarding the actresses with various fluid simulations throughout the duration of the movie.
jinchoung 6 months ago
Imagine this integrated with high end Movie cameras. I have no doubt that special effects would take a giant leap forward.
lifer86 6 months ago
Comment removed
Run3scaped 6 months ago
this is a fucking win for 3d modellers. get a lazy susan, put your kinect next to it, spin round object.
BAM.
you have just modelled a bacon sandwich.
dillzy1986 6 months ago 133
@dillzy1986 Gay baconstrips! You watch epic meal time?
kennethsonnek 6 months ago
@kennethsonnek my muscles and glasses say yes
dillzy1986 6 months ago
@dillzy1986 then 3d print it
forresto 6 months ago 10
@dillzy1986 Ehh. I don't think so. If it was that easy they'd have some intern do it and send the modellers out on the street to save cash.
weggles 6 months ago