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.
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?
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.
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.