Slashdot Mirror
Photosynth Team Does It Again
STFS found an update to the
Photosynth stories that we already ran. You might remember the amazing photo tourism demos. Well, this new version kicks things up several notches with paths and color correction to more smoothly transition between photos taken in different lighting conditions. As before, this stuff is worth your time. Check it out.
The color matching section was quite impressive given the wide variety of lighting and color temp in the starting photos; if they wrote their own software to do that, it sure counts as R/D.
No good deed goes unpunished. - Avon, Blake's 7
And THIS is why I tend to take huge numbers of photos and never delete any... Technology like this will account for easy geotagging, date I already have in the EXIF data, whereas people can be tagged with face recognition soon enough.
That done, I'll be able to navigate my tens of thousands of photos by asking for things like photos taken of the kids while outside at the cottage when they were 3 years old.
Also, remember to backup! :)
.: Max Romantschuk
Very cool stuff! Does anyone know (are any of the project team members here?) how much foreknowledge of the object being orbited that is required?
For example, is a 3D wireframe model necessary?
Is a filtering of the photos necessary to ensure that they are all of the same subject?
What level of pre-processing is required on the photos, either automated, or manual?
How well does the system fare when the object being photographed isn't absolutely static? A drawbridge, for example, changes shape. Or Niagara Falls. Or a flag. Or a single person.
Anyone know?
Put my fist through my alarm clock with its ding-dong death inside my ear. - The Blackjacks.
Science fiction and VR have primed me to believe someday we would all be walking around some imaginary digital world (oh wait, WoW anyone?), but this is "virtualization" of the real world. Like Google street view on crack. I am simultaneously in awe of the technological achievement and embarrassed that my life in computers hasn't yet created anything so cool.
I, for one, welcome our new PhotoSynth overlords.
Help fight poverty: Punch a poor person.
Shut The Fuckup Sonny - it's what the old guys on Photo.net say when you tell them that photography as we know it is dead - especially if you mention film in the same sentence. It'd be like saying that BSD is dead here on /..
Seems a bit simplistic to me, I'd have thought that they'd turn the photos into a virtual world, using the colour corrected photos to create wireframes and bumpmaps and then being able to apply whatever lighting and other effects to the world. That allows you much more freedom to use other methods (e.g. LIDAR) to populate the database.
Creating 3d models also allows you to remove transient objects (people), or add objects to the scene, e.g. what would David look like on the empty plinth in Trafalgar Square.
I suspect the reason they've done it this way is more about the patents than practical application.
**TODO** Steal someone elses sig.
It looks like taking a video would be easier. That way, you wouldn't have to spend time stringing all the stills to together - if I understood correctly.
goatse
Awwwww Christ ... now you've put zooming and panning into my head at the same time as goatse.
Thanks.
If libertarians are so opposed to effective government, why don't they all move to Somalia?
I was on an ocean cruise recently, and a little girl was lost... Ship's Security were looking for her.
I later heard she had been found, and as I walked back to my cabin I thought of this software.
Every corridor of the ship has cameras.
The parent could recall the last time she was with the child. An operator could then fly through a 3d map of the ship, from that point in time, with recorded video overlaid, following the girl in fast-forward until the current time was reached.
The flying would be like spectators do in first-person-shooter type computer games.
An observer could even be automatically tethered to the missing person.
Microsoft had better not repeat google's slight miscalculation. The credits given to the flicker accounts tell that they must of had to opt in, unlike streetview. This photosynth system would be incredibly powerful if it used all flicker images or crawled the web. People are clearly visible everywhere in this system, and some may become upset.
I've seen some of these articles about Photosynth, and there seems to be a lot of hype. But... I don't get it.
I see that Photosynth can glue a series of images together so that you can zoom into and move around a scene and get an epileptic-seizure of correlated viewpoints. This group seems to have made a virtual walk-through using this. But I am unclear:
1) What is the point
2) What is the breakthrough
As for #1, Photosynth is ugly. I would much rather have a few good quality same-lighting photos to look at than to have my eyes torn out trying to make sense of this. So unless my brain works differently from everyone else's, the point is not an aesthetic one. It must be a technological one. Is it the promise that we could one day use this to combine amateur images into a real 3D image? Why would this matter when doing that with professional images is easy to do and looks much better?
As for #2, without reading the entire paper I'm unclear how much of this was done automatically. If someone manually entered the GPS coordinates and direction of these photos and then wrote a program to glue them together, I see a lot of hard work but no science. If this required creating a rough 3D layout and it was able to extract the positions programatically, then that is impressive. If it was able to make this entirely from nothing other than the images, then holy moly that's amazing. But I can't tell from the video which of these it is.
Can someone explain this to me and why I should be interested?
Obligatory link to the youtube video (not a rickroll, I promise!)
Thanks, Network Mirror!
It's a bit dense and involves some cross references, but here's a part which may answer some of your questions. For more detail you oculd always read the paper yourself.
Erm, isn't that a bit of a long winded complicated way of doing things ? I mean sure, Computer could do that for you but why not just ask instead ?
"Computer, where is " and that would be that. I mean typically she'd be stowed away in the engine room re-configuring the sensor array for some nefarious purpose but that's just kids nowadays I guess.
I imagine that's the ultimate goal. But what they have now is still amazingly impressive...
The next step in that goal would be making it automatically determine what's in the structure, and what's 'in the way' (a tourist, a security guard, a pigeon...). It would be annoying if a tourist was thrown in with the 3-d model if they happened to populate the set with a ton of pictures of them and the object you want modeled.
Still, as it stands now, it's still an amazing way to experience a historical landmark that maybe you can't afford to visit. Imagine showing your kids the Parthenon, the Sphinx, the Great Pyramid, The Statue of Liberty, and the Kremlin. Not some static pictures, but a 3-d experience, photorealistic (Because it's populated by photographs, natch). It's the same kind of thing that, if I saw it in a movie 10 years ago, I'd have laughed at it for being stupid, because computers can't do THAT...
There was some discussion recently about the possibility of building an open source photosynth - and creating an 'open voxel space' map of the planet.
Anyone know if there's been any progress on this?
http://lists.burri.to/pipermail/geowanking/2008-June/005373.html
Yes, and this is nothing like that. That was apparently creating additional information that simply wasn't in the original photo. This is using a whole bunch of photos of the same scene, taken at different times, angles, etc to automatically build up a 3d model. Nothing is being enhanced, you're "merely" being shown the most appropriate, pre-existing photo based on your location and view direction in the generated 3D model.
Damn cool tech, but not the same as that used in Blade Runner (or CSI, or any other "enhance this photo to make that illegible squiggle that's beyond the resolution of the photo readable" plot device)
It's official. Most of you are morons.
You just give it the photos - it figures out the rest. It works by stitching them together in 3D, so if there is a photo of one part of the subject that is not overlapped by one other, the photo won't be part of the finished "model". If you download the old demo, you can see the Yosemite demo, which shows what happens with movement (hikers climbing a mountain). If it can match up most of a scene in an image, the image can still be used. I'm sure it'll only get better. Another great example is in the old demo, where they simply searched Flickr for "Notre Dame", and then constructed the entire cathedral. It picked up a photo of a poster in someone's house, and seamlessly integrated it into the model. It recognised what it was from, and where on the cathedral it was positioned, and reflected that by putting that image exactly where it should be in the finished "model". Of course this is just stuff I've gleaned from watching the demo videos, using the demo, and reading as much as I can about it, so I might be wrong on some of it, but that was the impression I got. If I'm far off, I'd appreciate being put right, as this technology is nothing short of stunning.
Microsoft have turned Photo Tourism into something incredibly more powerful. But don't let that get you off your high horse. Some of us don't play the "them" and "us" game.
Huh? Why not get out there, meet people from those countries, eat the food they eat, get drunk with them, and actually experience the world?
Of course! Because every familiy has the time and resources to visit every possible interesting place on the planet.
Huh? Why not get out there, meet people from those countries, eat the food they eat, get drunk with them, and actually experience the world?
Ummm, because we can't afford it? Taking six people to Greece would consume our family vacation budget for 3-4 years. I'd rather stay closer to home and spend more time with my kids.
Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
That done, I'll be able to navigate my tens of thousands of photos by asking for things like photos taken of the kids while outside at the cottage when they were 3 years old.
That raises an interesting concept. Could they do a 4D orbit? For example identify pictures of your kids at different ages and then you could watch them grow up in front of your eyes. Or watch how a city street changes over a decade? That would be really interesting...shame it will probably only every be available for Windows.
I thought one of the previous stories said it would do that.
What I was curious about is, how? A distinguishable photograph could be associated. But, even with one of the examples in the display, the Statue of Liberty, if this is automated, how would it be able to distinguish the real statue of liberty with say a souvenier sitting on my coffee table? Basing it on size and distinguishing shapes, it would match either one. Basing it on those, and the background objects is impossible. It already has to take into account that there are changes in the foreground (people, extra objects like light poles that are not present in very similar views). Background objects like clouds come and go, and leave entirely different images.
For not quite as distinguishable objects, it would be a lot harder. Say you used the Statue of Liberty as your starting point. If you were to travel into Manhattan, there are many very similar shapes for buildings and storefronts. Sure, unique buildings would be obvious, but for every obvious building, there are dozens of almost identical buildings.
Even then, you would have to know the city. Similar architecture can show up in a variety of cities, and be close enough to match. Cameras may record timestamps embedded in the original image (assuming unedited photos are added to the system), but there is nothing useful like geographic coordinates included.
All the photos were shot from the same perspective. It was as if they were shot by one or more photographers of about the same height. There should have been a more significant change to the view from say a 4' tall child to a 6'8" tall man. I don't claim to be a "great" photographer, but I'm pretty good. One of the essentials between being someone who can take snapshots, and someone who can take photographs, is making the composition of your photograph to illustrate the view. That frequently involves changing height and view. Maybe you want to lay on the ground for one, and climb on a ladder for another.
I took some photographs at the World Trade Center on 9/9/2001. Those photographs aren't just of the skyline, although I did take some snapshots at the time. Some are composed lookup up towards the top of the buildings from the ground, and down while leaning on the glass of an observation deck window. Photography isn't documenting a first person view. It's beautifying and romanticist a view, without necessarily changing anything about what's in the composition of the photograph.
There are other features that I don't see how they're getting, such as the zones where photos were shot from. That takes an awful lot of extrapolation. What's the difference between a photographer 10 feet away, and a photographer 200 feet away with a good zoom lens? Almost nothing, except maybe a little focal distortion at the edge of the photo. That varies with the quality of the camera and lens anyways.
I did a little project once years ago. I was sitting in the hills just under the Hollywood sign. We were sitting on top of a hill, so I had a good panorama view. I tried to keep the horizon centered, and I shot frames the whole way around. When I stitched them together in Gimp, I noticed that each frame had variations in it's color. It wasn't because of AWB, it was because the camera (good for the time) had some weird variance, so there was a difference in color from the left to the right side. So, two shots from the same camera at the same settings were significantly different.
I would be willing to suggest that the demo shown isn't a demonstration of a functional piece of software. It is a good example of what can be generated with a computer. I could do the same thing in Gimp or Photoshop. If my job let me play like this for a few weeks, I could have made a better example of vaporware.
Serious? Seriousness is well above my pay grade.
There are other features that I don't see how they're getting, such as the zones where photos were shot from. That takes an awful lot of extrapolation.
I suspect it isn't as complex as you think - exif tags usually include focus distance and focal length. Also included with that is sensor size or camera model, which will tell you effective focal length.
When you combine that info with the apparent size of the object in the photo (i.e. statue of liberty is x percentage of the frame high), you should be able to get a reasonable estimation on where the picture was shot from.
For relatively isolated objects (like the statue of liberty), I'd assume you'd need a single shot w/ a known location to act as an anchor (it's possible with cameras that support gps) - but I wouldn't be surprised if a mathematician could get around that. Perhaps angle of the sun at time / date (exif again), but I'd assume that would take significant processing and have all sorts of things that would screw it up.
I know DXO can analyze a jpeg or raw to get the model of a lens - presume it's stored in exif somewhere - and lens distortion can be corrected w/ a x% pincushion adjustment to the photo based on known values - DXO has a fairly huge database and I wouldn't be surprised if they were using some of their tech.
Either that or the guys here fudged it by only using pictures from a specific make / model of camera.
I suspect that they would use the distance estimation in exif to eliminate the statues, etc - although I'm guessing a fair number of statues would be eliminated because they aren't scaled properly. Autofocus distance estimations can be off, but not usually hundreds of meters off.
As for cross photo whitebalance / color gimpiness across the frame, that can be relatively easily corrected - autostich (free) and autopano pro (the "pro version" of autostitch) does it and they've licensed their stuff to a bunch of other companies.
Also... keep in mind they really aren't displaying high res imagery - so they can estimate / tweak a bit. I don't know if that will scale, or if it does, what the processing requirements will be, but it's probably not a huge concern.
It's clearly not as simple as they try to make it (they really only used a small amount of image sets), but I don't think it's a photoshop job.
The question is whether it will scale.
1q2w3e4r5t6y7u8i9o0pqawsedrftgthyjukilo;p'azsxdcf
Could it be used to piece together a massively high resolution, totally nude, 3d model of a famous celebrity from the millions of event photo's and nip slips? ;)
NTSC is worse than you described; you have two 1/60th second exposures interlaced together. Utterly worthless for still frames.
Once progressive HD video cameras become cheap, then video will suck slightly less for the average family archive.
Ok folks, don't worry!
Just keep chanting the mantra that Microsoft never innovates anything and everything will be ok.
I'm sure there will be a linux port of this soon and then we can all go back to complaining about how Microsoft copies everything from Apple.
There are other features that I don't see how they're getting, such as the zones where photos were shot from. That takes an awful lot of extrapolation. What's the difference between a photographer 10 feet away, and a photographer 200 feet away with a good zoom lens? Almost nothing, except maybe a little focal distortion at the edge of the photo. That varies with the quality of the camera and lens anyways.
Perspective changes a lot based on where the camera is, a big zoom lense does nothing to change the perspective it just makes the image larger.
Their process finds machine recognisable points in each photo, then looks for matching points between photos. Once you know that 2 photos are of the same subject you can use the separation between these known points to work out the relative viewing position of each camera. It only takes about 4-5 common points on different planes to pinpoint where each camera is relative to other camera's. I can visualise how this process could be completely automated.
At the end of the process they have a 3D model of where all these identifiable points are relative to each other, and they know where to project the plane of each photo within that model.
09F91102 no, 455FE104 nope, F190A1E8 uh-uh, 7A5F8A09 that's not it, C87294CE no. Ah! 452F6E403CDF10714E41DFAA257D313F.