Computer Created A 'New Rembrandt' After Analyzing Paintings (bbc.com) 115
TechnoidNash quotes a report from Techie News: Rembrandt van Rijn was one of the most influential classical painters, and the world lost his amazing talent when he died nearly four centuries ago. And yet his newest masterpiece was unveiled only yesterday. How? By scanning and analyzing Rembrandt's works, a computer was able to create a new painting in near-perfect mimicry of Rembrandt's style. It has been named, appropriately, "The Next Rembrandt."
The computer used machine-learning algorithms to create the portrait, which was then 3D-printed to give it the same texture as an oil painting. "The Next Rembrant," was a collaboration between Microsoft, ING, Delft University of Technology and two Dutch art museums -- Mauritshuis and Rembrandthuis.
What was that shit site? (Score:5, Informative)
Re:What was that shit site? (Score:4, Insightful)
...felt like a throwback to the days when people actually built "sites" with Flash...
It's not nearly as bad as that.
* browser navigation keys work (doesn't get stuck in a separate mode)
* Text can be selected and copied
* No proprietary player brimming with exploits
Agree, it doesn't cater to the ADHD set - you actually have to play the video, or at least skip through to the end like I did - to test your art connoisseur quotient, or scope the tech out for counterfeiting potential, or whatever your immediate goal is. You have to admit, it's a slick html5 demo, and not without taste.
It also breaks the internet in various ways just like flash, for example, no deep links, you can only bookmark the top level site. The only way in is through the art show. I sure don't want the internet to end up like that, a video internet just isn't for me. But for announcing an art research project? OK, fine. At least it's not flash.
Re: (Score:3, Informative)
It's worse than that: It bitches about my browser being too old or hey, would I like a windows binary of chrome? (This is a linux binary of chrome, yech.)
Anyway the painting reminds me of a story: $GUY's father in law has a Mondriaan on the wall, and as a prank he copies the painting himself. "Funny" says father in law, walking by the painting and unaware of the swap, "always thought it had a special something, but that's gone now."
"Analyzing" and coming up with a "new" painting in the same style? Sure, goo
No, it didn't. (Score:2)
Computer Created A "Rembrandt-Themed" Graphic After Analyzing Paintings
Why? Because art is all about the artist attempting to elicit an emotional response from the person experiencing their work, and since no so-called 'AI' has actual emotions, it can't understand art, and therefore can't 'create' art.
Re: (Score:3)
But can the AI itself then be considered art, as it has been made to make people observing it in action feel awe and astonishment at what it is doing?
Re:No, it didn't. (Score:5, Funny)
Re: (Score:1)
I suppose code could be considered art. After all Windows has elicited great feelings of despair and anguish from those observing it.
The geek's jokes just write themselves, no need for computer simulation. It would be unkind to suggest that he has had twenty years to stake his claim to the desktop, with next to nothing to show for it, and if that isn't cause for despair, what is?
does it look like a data dump set to color? (Score:2)
because that's what it is. "here's a line with a little curl, so it has to have a thick edge here" is all they were doing.
Re: (Score:3)
But can the AI itself then be considered art, as it has been made to make people observing it in action feel awe and astonishment at what it is doing?
It really depends on your definition of "art." I can "observe" a waterfall or an erupting volcano "in action" and "feel awe and astonishment at what it is doing."
Are they "art"?
I know what you mean, though. For most people, "art" has something to do with a special kind of "aesthetic" appreciation. If you are able to appreciate the actions of a computer program in that aesthetic fashion, then sure, why not call it "art"? For some, there are certain things that are always "off-limits" for that kind of
Re: (Score:2)
Are they "art"?
"Whenever somebody puts quotation marks around the word art, I imagine a stuffy guy with a square jaw glaring at a Maplethorpe photograph. And through his twisted, disgusted sneer he says "they call this 'art'! Can you believe it! 'Art,' they call it!" And he stands there, being disgusted for hours on end, just staring at it..."
Re: (Score:3)
Because art is all about the artist attempting to elicit an emotional response from the person experiencing their work, and since no so-called 'AI' has actual emotions, it can't understand art, and therefore can't 'create' art.
Even if I accept your narrow definition of art as "elicits and emotional response", I can't accept your non sequitur: having emotions is not a precondition for eliciting an emotional response. Just consider a flat tire to know that.
Re: (Score:1)
A.I. can elicit emotion easily.
Many of the notes, chords, colors, and expressions which elicit emotion are now known and can be automated. A computer can generate original 'sad' or 'inspiring' music without human input. And that's without much in the way of A.I. either.
speaking of flat tires, have you seen "Rubber"?
I feel like we are closing in faster on A.I. over the last 5 years than the prior 20 years. The brain is a collection of many subsystems integrated in the claustrum.
Brain injuries are especial
Re: (Score:2)
The jury is still not out yet on whether the human mind is a procedural deterministic program. A bit too early to say it's definitely not AI.
Re: (Score:1)
The brain has a lot of short cuts for speed (See a book called Brain Bugs.)
There is plenty of evidence that the brain is it. There is no supernatural or extra dimensional component to the brain.
I suspect that parts of the brain are procedural and deterministic but with shortcuts. Other parts are parallel and other parts are neural networks. There may be parts we dont' understand how to model yet too. But progress is faster now than in the past.
Every year I see more AI goalstones met and then declared t
Re: (Score:2)
Because art is all about the artist attempting to elicit an emotional response from the person experiencing their work, and since no so-called 'AI' has actual emotions, it can't understand art, and therefore can't 'create' art.
Even if I accept your narrow definition of art as "elicits and emotional response", I can't accept your non sequitur: having emotions is not a precondition for eliciting an emotional response. Just consider a flat tire to know that.
Indeed...
https://www.youtube.com/watch?v=E0mBxtWQR7M [youtube.com]
NOT elicit an emotional response from the person (Score:2)
To relay artist's PERSONAL experience to another person.
That's why the goal is to UNDERSTAND art - not to love it or hate it, as it would be if the goal of art was an emotional response.
Re: (Score:2)
and since no so-called 'AI' has actual emotions
Please explain what emotions are and why they can't be represented by AI.
Re: (Score:2)
Art is about creating an emotional response in the viewer *regardless of the intent*. In fact many times art (literature in particular) evokes an emotional response entirely different from the intent or when there was no intent at all.
No emotions in the artist are required.
Re: (Score:2)
You're making the incorrect assumption that a computer needs to experience emotions in order to elicit them in others.
Nope, sorry (Score:2)
The brilliance of a painter like Rembrandt can not be reproduced digitally. The talent of a painter is only partially based on color and space utilization, but primarily based on brush strokes.
Build me a robot that uses a mechanical brush with the same finesse, then we will talk.
Digital mimicry is interesting, but it's not painting.
Re:Nope, sorry (Score:5, Insightful)
Re: (Score:2)
You are not a painter if you don't paint, you are not a guitarist if you don't play a guitar, and you are not a boxer if you don't box.
No issues with the digital world at all, but call things what they are and keep your feet on the ground and head out of the clouds. Rembrandt was a painter and artist. There were no online databases of paintings, and no store to order paints from. Classic painters mixed their own paint and colors, and mechanically crafted from scratch.
Re: (Score:1)
Rembrandt did not, he married into wealth and bought most of his supplies. He lived in the city and employed people to do the dirty parts of art for him.
While you are correct in the sense that rembrandt was a classic painter, and the idea that classic painters had to make most of their own supplies, but once you got wealthy/renowned enough (and rembrandt was fucking REMBRANDT), you just had other people do that shit for you.
Kinda like we do now.
Credentials: Art BFA
Re: (Score:2)
and rembrandt was fucking REMBRANDT
For fun or for the sole purpose of procreation?
Re: (Score:2)
He was fucking himself. I'd guess it was for fun.
Re: (Score:1)
Lt. Cmdr. Data: Strictly speaking, sir, it is not my playing. It is a precise imitation of the techniques of Jascha Heifetz and Trenka Bron-Ken.
Captain Jean-Luc Picard: Is there nothing of Data in what I'm hearing? You see, you chose the violinist. Heifetz and Bron-Ken have radically different styles, different techniques, and yet... you combined them, successfully.
Lt. Cmdr. Data: I suppose I have learned
Re: (Score:2)
2. As much as I liked NextGen, it was just a TV show, not real life, there was no such actual personage as Mister Data, we're not in the 24th century, there's no Federation of Planets; it was all fiction.
3. I stand behind my original assertions.
Re: (Score:2)
Indeed. This thing is part of some sort of campaign (non-organized, is my guess, but still targeted) to make people accept digital fakes of real things as the genuine article. As usual, the motivation is greed. In the same fashion we will eventually get digital "actors", "writers", "game designers", etc. and the quality will be sorely lacking in all of those. A large part of the customer-base will not notice that though.
Re: (Score:2)
Umm... this one? I mean, sure I grant it's using a motor with much finer control than a brush, and extruding the ink in a controlled way, but both are being done to emulate the clumsier human motions of a hand with brush.
Re: (Score:3)
It's not just digital. There is a physical, 3d printed, picture with a texture which is presumably mapped from Rembrandt brush strokes.
I'd like to see something more complex (Score:2)
A more complex staging and ideally of something that could not have existed in his time.
I don't know... a dutch programmer riding a t-rex. In Rembrandt's style.
The point is not to make a Rembrandt forgery I would hope. The point should rather be to capture the style of the artist and give the computer or other artists the ability to generate works in that style.
Wrong format (Score:1)
it is a Rembrandt only if computer is Rembrandt (Score:2)
until computer has the same individual personality ,memory, intelligence , and emotions( including troubling ones with all the psychological complexes that come with experiencing life ) as Rembrandt, the painting created by it is not a Rembrandt.
one has to wonder why they chose painting to demonstrate this computer abilities (with added complexity of physical creation of painting which is mostly dependent on other technologies), when poetry would have been a better way to demonstrate the computer's mach
Re: (Score:2)
claim that a new work can be created by computer with same quality and recognizable individuality, as a work by original creator
Re: (Score:2)
no wonder you post as AC, since you obviously can't comprehend what you read.
Typical, average, math (Score:5, Insightful)
It's funny. This research spent a great deal of effort to identify the artist's "typical" approaches to individual and compound features; it then averages them to produce a work that feels like a Rembrandt.
But the only reason that it feels like a Rembrandt at all is because it is the centroid of all of his stylistic approaches -- a perfect average.
As in most cases, an "average" of many details is precisely not what an artist does. An artist's real work is in the details that defy their own averages and typical approaches. Listen to any artist analysis, and you'll hear words like "unlike in his other works...", "for the first time at that point..", "never before...", "...and yet in this painting...".
This work is very impressive, a perfect way to fool viewers and a perfect way to pay respect to Rembrandt's approach. That said, however, it is precisely the definition of not a Rembrandt. It is not the work of an artists. It is the work of a business -- which has always been the ability to reproduce copies of something (product or service) in a replicatable and bulk manner.
Re: (Score:1)
That said, however, it is precisely the definition of not a Rembrandt. It is not the work of an artists. It is the work of a business -- which has always been the ability to reproduce copies of something (product or service) in a replicatable and bulk manner.
Actually it is a perfect Rembrandt. He was a businessman: most of his work was pained by his students - he was just signing them. If he would have this program connected to a robot which would "do the painting" (he probably would not get away with a laser printer), he would save quite some money to keep his students silent, increasing ??? Profit!
Re: (Score:3)
It's funny. This research spent a great deal of effort to identify the artist's "typical" approaches to individual and compound features; it then averages them to produce a work that feels like a Rembrandt.
But the only reason that it feels like a Rembrandt at all is because it is the centroid of all of his stylistic approaches -- a perfect average.
That's one way of looking at it. But actually the methodology as described in TFA was more to combine thousands of fragments of other paintings to create a composite.
I wonder if the result is therefore a little like the musical "compositions" created by the algorithms of David Cope [wikipedia.org]. Cope has been doing this procedure since the 1980s where he has a program that takes dozens or hundreds of musical works by a particular composer in a particular genre as "input," and then claims to "compose" new works in th
Re: (Score:2)
Also, it's unclear how much tweaking was involved in this project
This is why I'm not impressed. Once they can tell the machine what to paint without tweaking, I'll raise an eyebrow. Until then, they've just created a different brush and canvas for humans to work with.
One very inefficient one too, in that it takes dozens of humans several years.
Re: (Score:2)
The project is a work of art, not the output. (Score:3)
I want to see it (Score:2)
I clicked on it and something animated is happening on my screen, but it definitely isn't a painting. What gives? Microsoft and all these brilliant computer experts can duplicate Rembrandt, but they can't distribute a digital image in a standard, easy to download format?
Re: (Score:2)
I don't get it (Score:2)
If an AI meshes together some bits and pieces of a painter it's news and maybe even art, but if a musician meshes together some bits and pieces of another musician it's a lawsuit?
Re: (Score:2)
Hey, don't attack me, I didn't claim copyright made any sense!
a new Gimp filter? (Score:2)
Were are all the Rembrandts? (Score:5, Interesting)
Re: (Score:3)
I like Yoko, but if she's a top artist, then we've fallen far from the days of Rembrandt.
Re:Were are all the Rembrandts? (Score:5, Insightful)
Something I often wonder is why we don't hear about 'new' geniuses in art. It's always the same guys from the 1700 and 1800s (once in a while an author from the 1900s sneaks in).
Uh, well, you might want to have a look here [wikipedia.org], where there are links to probably a couple hundred painters of the 20th century who are regarded as significant. There are many people in the art world who consider a lot of them to be "geniuses."
Now, your objection might be: "Hey, most of that stuff looks like crap compared to Rembrandt. Where's the good stuff like what he did?" Certainly many people feel that way about various artistic movements of the past century or so.
And for that, you'd have to blame German Romanticism of the 19th century, and "the cult of the genius." It's interesting that you use that word "genius," but artists weren't always seen that way -- Rembrandt wouldn't have been referred to that way in his lifetime. Artists used to be viewed a craftsmen, with particular skills -- some more talented than others. Centuries ago, being a painter meant learning the latest skills -- paint and materials weren't as good as they are today, so you needed to exploit the technology they had. Knowledge of perspective or the ability to manipulate and represent light and shadow took time for artists to figure out -- and so there was a gradual evolution toward the ability to create more realistic representations. The best painters were the ones who had incorporated this new knowledge to hone their craft.
That all started to change with the "cult of the genius" and the "Aesthetik" movement that began in late 18th-century Germany and spread during the 19th century. The emphasis went away from craftsmen participating in guilds or groups of people with knowledge, and more emphasis was put on the individual creator ("genius") who was supposed to demonstrate individual expression.
All of this is to say that there are hundreds of artists that could easily paint a Rembrandt-style painting today, probably as good as this computer did if not better. And there are probably thousands with the talent to learn how to do it easily, but they have no desire to.
Why? Because that would just be "derivative." It has already been done. The mastery of skill and technique is considered only what one does in school -- to become an "artist" today requires innovation. Painting a realistic expressive scene with interesting chiaroscuro like Rembrandt is a great "exercise," but the "geniuses" of the 20th and 21st century wouldn't be caught dead doing that as their own output -- unless they were doing it ironically or something.
TL;DR -- Rembrandt wasn't a "genius," since that whole concept of artist as "genius" hadn't yet been invented in his lifetime. And there are plenty of modern folks people call "artistic geniuses" -- but usually because of their unique innovations or individual ideas of expression, which are often quite different from the goals of someone like Rembrandt.
I get that if I'm in the scene (Score:2)
Re: (Score:2)
You've likely heard of Monet and Picasso. Plus the ones we make fun of: Rothko and Pollock (and you've probably seen Mondrian, whose work is too bland to remember), who suckered the world into thinking meaningless blobs of paint were valuable art. Best con artists ever.
Re: (Score:2)
Re: (Score:1)
Shame on you. In just 1 minute I can name Norman Rockwell, Gil Elvgren, Pablo Picasso, and Andrew Loomis. Then there are artists like M. C. Escher, that were not 'painters' in the strict meaning of the word, but still deserve a mention.
Re: (Score:2)
Something I often wonder is why we don't hear about 'new' geniuses in art. It's always the same guys from the 1700 and 1800s (once in a while an author from the 1900s sneaks in).
Uh, well, you might want to have a look here [wikipedia.org], where there are links to probably a couple hundred painters of the 20th century who are regarded as significant. There are many people in the art world who consider a lot of them to be "geniuses."
Imagine if you will that everybody you know only listens to classical music and they only listen to works written before 1900. You have never even heard of The Beatles, for example. Everybody you know probably would tell you that all "modern" music sucks and you would be pretty much baffled to identify works by people like Jimi Hendrix, The Rolling Stones, The Doors, Nirvana, etc. That's kind of how art is. Starting in the latter part of the 1800s there was the impressionism movement and some other move
Re: (Score:2)
They are there, you're just not moving in the right circles to hear about them. And typically we only hear about these geniuses after they're dead, when they have a body of work behind them that somehow qualifies them. The art world is full of art, there were more cubists than just Picasso or surrealists like Magritte but somehow they became the most famous ones, both of them I think through controversy.
We hear about a handful of people even in history because they're famous for some stolen, missing or opul
Re: (Score:2)
Re: (Score:2)
Some time well before 2000 the techniques of photo-realism and trompe l'oeil were perfected,
That's the excuse often given, but there were few artists who could match photo-realism......abstraction and 'style' were a way for artists to be successful without reaching quality technique.
Re: (Score:2)
That's the excuse often given, but there were few artists who could match photo-realism......abstraction and 'style' were a way for artists to be successful without reaching quality technique.
That's overly harsh. It's certainly true of some artists, but as I explained in my post above in the thread, there's an expectation that was created sometime around the 19th century for continuous "progress" and innovation in art.
Why bother spending years learning classic technique only to be branded as "uninteresting" and "derivative"? Sure, if your goal is to paint portraits or to sell somewhat realistic landscapes at a county fair, that's a useful skill.
But if you wanted to be accepted as an "artis
Re: (Score:2)
But if you wanted to be accepted as an "artist" by the elite judges who control the artworld, those classical techniques are often less relevant. I have nothing against classical techniques, and I think they are worthwhile anyway
But I do have something against the elite judges who control the artworld....they are garbage and their judgement sucks. Better to be a no-name at the county fair with real skill than to have to bow to those losers.
Realism gives you more options, more possibilities. Monet couldn't have done his incredible garden paintings if he hadn't mastered realism first, and Picasso knew exactly what to leave out because he could paint exactly to begin with. Realism is easier than abstraction if you want to do it rig
Re: (Score:2)
Now if you want to become an artist, there is not a lot of work for you. Portraits are rarely done, signs are created by computers, paint
Re: (Score:2)
We live in a big world with so many skilled people that it's much harder to stand out.
https://www.artrenewal.org/ [artrenewal.org]
Re: (Score:1)
artist beware (Score:2)
By artist, of course, I mean anyone in a creative field- painter, writer, musician, architect...
This is another quantum (incremental) step toward computer generated art. Music has been done, writing, some graphic art. As in this example a study of a technique, a style, a mood is enough for clever software to imitate originals. For instance *your* style of writing, as revealed in term papers or creative writing, can be identified accurately and that ransom note will expose you to the authorities.
The hope for
Re: (Score:2)
Exactly: these articles always make silly claims about making artists obsolete because now computers are "just as good" as the artists. But the touchstone of art is innovation. Algorithms have been able to copy established artists for decades, and students have been able to do it for thousands of years. Listening to Bach and reproducing Bach is clever, but I'll be really impressed when a computer can produce Bach after it listens to Palestrina. That would require computers that can understand human taste, h
Copyright? (Score:2)
Name-dropping (Score:3)
This is a classic case of name dropping to make the software seem more amazing than it actually is.
Lots of students in art classes can copy the work of a famous painter, and even imitate the style. Some can even do so convincingly. But that doesn't make the student a "new Rembrandt," in fact, most such students will never be recognized as brilliant. There is much more to being a master artist than just imitating the style of a great painter.
Re: (Score:2)
Han Van Meegeren [wikipedia.org]
Not as impressive as it first seems (Score:1)