Slashdot Mirror
Google Unveils 'Gigapixel' Camera To Preserve and Archive Art (thestack.com)
An anonymous reader writes: The Google Institute has developed an ultra-high resolution gigapixel Art Camera which can automatically recompose images into single works of extraordinary detail. The first thousand images are released today, and include works by Rembrandt and Van Gogh. A gigapixel contains over one billion pixels, providing a level of detail unavailable even to the naked eye. The Art Camera has increased the number of available gigapixel art images from 200 to 1000 since 2011. The Art Camera consists of a robot camera that automatically takes hundreds of high resolution close-up photos of the details of an image, using laser and sonar technology to ensure that each image is in focus. Software is then used to take the hundreds of individual close-up pictures and combine them into one whole image. With this technology, one can view photos produced by classical artists from a computer or mobile device without needing to travel around the world to do so. These digital gigapixel images are intended to be available for viewing and studying for years. In the future, we may see Google use machine-learning algorithms to analyze influential classical painters and create new masterpieces.
Only people intending to pirate these works would need that kind of resolution. I expect Getty to file suit by Monday.
Is it just my observation, or are there way too many stupid people in the world?
In the future, we may see Google use machine-learning algorithms to analyze influential classical painters and create new masterpieces.
Nope, nope, and hell, no. At best they might create 'in the style of such-and-such classical artist', but they won't be 'masterpieces'. Google's hubris, arrogance, and lack of taste, apparently, know no bounds. AI fanbois can bite me.
Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
It is not a "real" gigapixel camera...
(today's largest are about 250Mp)
Sure, as long as you can always redefine "Real AI" to mean whatever we haven't yet done.
We hope your rules and wisdom choke you / Now we are one in everlasting peace
Well since we don't have any AI at all yet you can comfortably say we haven't done anything.
Sure, a painting isn't just an image. It has a texture, smell, and taste too. Most museums won't let you experience those however, so the image is pretty much what you're limited to either way.
We hope your rules and wisdom choke you / Now we are one in everlasting peace
Ok, have fun playing with your own special definition of AI that no one else uses.
We hope your rules and wisdom choke you / Now we are one in everlasting peace
Have fun playing with Siri and your Go "AI" programs...
Exactly. The only thing worse than a tech nutter is a space nutter who says we are going to start populating other solar systems "real soon".
So you agree - modern artists blatantly stealing the methods and means of other pioneering researchers in the visual arts who are likely not to receive a single cent of remuneration for their discoveries? I'll bet as a result of this rampant piracy and IP theft, not a single one of the old masters will have the money - or will - to create any more great works. And it will be the fault of the pirate corporation Google, leading and encouraging mass - illegal - appropriation of the IP of others for personal, professional, and financial gain. /s
Is it just my observation, or are there way too many stupid people in the world?
A gigapixel is exactly one billion pixels, not "made of over one billion pixels". We should not let marketroids get away with this sort of crap.
While the overall result is impressive, the "stitching" isn't perfect. On most pictures it's hard to tell since the brushstrokes have lower resolution than the photography. But on one picture in particular, called "O Livro (os Cem)" by Jac Leirner (1987), the stitching irregularities are easy to find. Type "O Livro" in the search box to find this image.
Essentially this picture is a giant canvas of words in Portuguese. (I speak Portuguese, and it starts off as a bunch of rambling thoughts on money and love, degenerating into what to me makes no sense).
Anyway, to pick an easy to locate spot where stitching apparently took place, find the line about 2/3 down that consists of a giant hexadecimal number (what the hell is that, anyway?). The line starts "D21D22C23..." Blow it up to maximum resolution. The first and second D, and the second 2, have alignment artifacts, and the lower portion of this starting string is slightly blurrier that the top portion. This even gives some insight into the algorithm, where you can see that it's desperately trying to align the top and bottom portions, even distorting or shifting some in-between parts to achieve the result.
Like how you can look at a specific item, then back out into a 360-degree view?
Why would anyone engrave "Elbereth"?
https://www.youtube.com/watch?...
John McAfee 'It was like that time I hired that Bangkok prostitute; to do my taxes, while I fucked my accountant'
Many companies have been stitching photos together to make a single larger high resolution photo for a long time and by the looks of it many of them do a better job as well.
As well as a 3D scan, you should take colour samples at a whole range of frequencies (not just 3, as an RGB camera does). You also need to measure how opaque / translucent / transparent the paint is, the amount of specular vs diffuse reflection, etc. Again, at a whole range of frequencies. There is a LOT of data that needs to be collected.
I'd argue that they actually need to combine this with hyperspectral imaging. Why? Just think of all the different pigments used. Could be interesting for serious art history research, even. (How many paintings have been spatially spectrographed, until today?)
Ezekiel 23:20
Machines with 64+GB of memory are still quite rare.
16GB desktop (unregistered non-ecc ddr4) modules are now available at reasonable prices, so you should be able to do 64GB on a mainstream desktop platform and 128GB on a high end desktop platform now.
I figure about £750 for the bits to build a computer with 64GB and about £1500 for the bits to build a computer with 128GB. Compared to the cost of pro camera equipment that is quite cheap.
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
Bets for how long it is until this technology is used for porn, anyone?
This brings back into my mind the photo-stitching work done by the Chudnovsky brothers about 15 years ago. Photo-stitching large mosaics has been around for a long time, but the work by these two mathematicians on the Unicorn Hunt tapestries rises to a much higher level.
The tapestries has been hanging for a very long time. During a restoration they were taken down, soaked clean, and photographed on both sides. (The back side, being against the wall and with a fabric backing on it, had much more vivid color.) But the resulting images were completely un-stitchable by conventional techniques - nothing lined up! The tapestry, being a textile, had relaxed and subtly distorted by being laid horizontal and cleaned. The tapestry was not a static image, but rather a dynamic, breathing object. The Chudnovskys applied serious math and computing power to subtly distort each image in the mosaic, cross-referencing the front and back sides, in order to get the threads to line up.
TL;DR. See this article for more details.
This Google camera, I'm sure, has very sophisticated stitching algorithms. But in the end, it is probably assuming that it is capturing images of a static object. I wonder how it would handle a similar challenge.
"a level of detail unavailable even to the naked eye."
Even? You make that sound as if the 'naked eye' was the highest possible resolution one could get before.
Slightly off topic question for the Slashdot crowd:
With the rise of large megapixel cameras and seemingly every photo editing program now including some form of panorama stitching function creating a gigapixel image is now getting trivial. How do you display such images? How do you present them on the PC? How do you present them online?
I've had some success with using the Google Maps API and an open source tiling solution. However that has a serious problem in that it only works with JPEGs which have limited dimensions and thus unnecessarily prevents you from hitting that gigapixel barrier on the horizontal image.
Does anyone have any suggestions, preferably open source for a way to display a gigapixel panorama online? I've seen one tool but the license cost was incredible.
Likewise on the PC what are people using? Irfanview is quite painful loading images. Google Picasa viewer seems to be doing a good job but then magically crashes when you get to pictures of a certain size. Windows Picture viewer craps itself on Windows 7, and outright butchers the image on Windows 8-10 by rendering a high res picture and then not re-rendering when adjusting the zoom resulting in patches of horrible aliasing.
What are people using for this?
"With this technology, one can view photos produced by classical artists from a computer or mobile device without needing to travel around the world to do so" Er...
Not really.
Skylake desktop CPUs (just coming out) support 64GB - older CPUs topped out at 32GB of RAM.
128GB would require the use of Intel Xeon chips (server class), so it's not quite common yet. High end workstations with server CPUs may have the ability to take 128GB, but only the latest mainstream CPUs can take 64GB.
Anyhow, you probably won't see that much art up there - as a condition for Google to scan it, the right to post it online is Google, and a lot of more famous art and museums don't particularly want that. So you're not likely going to see the Mona Lisa scanned like that - the Louvre would rather you look at it in person or at low res photos they authorize.
Okay, really curious on this one. I've looked at a few of these now at fully zoomed in detail. WHY did they use a camera with cheaper glass to do such a high detail scan of these works of art? Zoomed in at 100%, the images are quite soft, similar to a budget or mid-teir DSLR lens. Basically, give a DSLR a few motors to move it around the painting, and it could do the same exact thing, only with sharper detail because of the higher quality glass available for them. Considering that their intent was visual image quality, it pretty much seems like their implementation was entirely constructed by people who don't fully understand optical properties of glass in relation to capturing photographs.
And another note: They really need to get their laser based auto focus system corrected. There were a couple times I spotted portions of the image out of focus.
"one can view photos produced by classical artists from a computer or mobile device without needing to travel around the world to do so." On what monitor do you expect to see a perfect representation of the original colors? Certainly not your mobile device...
I am not a number - I am a free man!
It's ok, we all know you are really Watson pissed that it isn't getting enough attention.
APK likes to ask for responses to the same things over and over. Maybe he just likes the responses?
Intelligence is easy, Cortana, Siri, Watson, you could call all of those intelligent. Wisdom, that is difficult.
APK likes to ask for responses to the same things over and over. Maybe he just likes the responses?
The only thing worse than those, is a nutter nutter. Someone so convinced of other people's shortcomings, that they are unable to get by their very massive shortcomings. Such as you.
APK likes to ask for responses to the same things over and over. Maybe he just likes the responses?