31–40 of 65 posts
If it were a -human- painting a fake Rembrandt, no matter how perfect an imitation, it would be called "a very very good imitation of Rembrandt" and nobody would claim that they'd in any sense brought Rembrandt back to life. Calling a very good forged Rembrandt a "new Rembrandt" would be pretty silly. Calling one generated by a computer a "new Rembrandt" seems just as silly. Just because it was composed by an algorit…
I'm curious why I cannot get hi res scans of old masterpieces I can use as wallpaper on my monitor. Doing image searches only turns up low res versions.
I'm curious why I cannot get hi res scans of old masterpieces I can use as wallpaper on my monitor. Doing image searches only turns up low res versions.
I'd guess that licensing such scans for quality reproductions is a source of revenue for museums.
I'm curious why I cannot get hi res scans of old masterpieces I can use as wallpaper on my monitor. Doing image searches only turns up low res versions.
They require you to make an account, but they have tens of thousands of public domain photographs of many of the artworks in their collection.
I feel like it's misleading of them to say that a computer painted the picture. That makes it sound like all works of Rembrandt have been fed into a Machine Learning algorithm and finally the computer spit out this piece. After having watched the YouTube video, I fell like actually the picture was more or less photoshopped together from existing Rembrandt paintings. The role of the algorithms was "only" to generate t…
I'm guessing recent progress in texture synthesis [1] and content generation [2] using deep convolutional nets made this possible. It would be interesting to see what was actually fed into the generating system. That would be a piece of art truly speaking magnitudes. [1] http://arxiv.org/abs/1505.07376 [2] http://arxiv.org/abs/1511.06434
You can read on their website [1] what they did, and seems that it involved a lot of manual labour still.
If it were a -human- painting a fake Rembrandt, no matter how perfect an imitation, it would be called "a very very good imitation of Rembrandt" and nobody would claim that they'd in any sense brought Rembrandt back to life. Calling a very good forged Rembrandt a "new Rembrandt" would be pretty silly. Calling one generated by a computer a "new Rembrandt" seems just as silly. Just because it was composed by an algorit…
Earlier quoted context omitted.
They said they incorporated the height map from the original. How did they obtain them? Do museums/galleries/owners let scientists or engineers study the layers of paint of the physical paintings?
Yes they let scientists study the layers. You can create hight maps by casting light from each side of the painting and using the shadows for your hight map calculations.
I think a flat bed scanner is great for creating those maps. Just scan your peace 4 times each time rotating it 90 degrees.
I'm curious why I cannot get hi res scans of old masterpieces I can use as wallpaper on my monitor. Doing image searches only turns up low res versions.
Check out: https://www.rijksmuseum.nl/en/search?s=objecttype&p=1&ps=12&... They require you to make an account, but they have tens of thousands of public domain photographs of many of the artworks in their collection.
If it were a -human- painting a fake Rembrandt, no matter how perfect an imitation, it would be called "a very very good imitation of Rembrandt" and nobody would claim that they'd in any sense brought Rembrandt back to life. Calling a very good forged Rembrandt a "new Rembrandt" would be pretty silly. Calling one generated by a computer a "new Rembrandt" seems just as silly. Just because it was composed by an algorit…
Now imagine reducing the correlation between the artificial brain and Rembrandt's brain until you reach the level of correlation to that of the machine described in the article. There will be a precise point where the paintings produced by the device will stop being Rembrandt's.
That is not to say that this machine is producing Rembrandt's. I am only saying that your reasoning is too simplistic.