Slashdot Mirror
Image Metrics May Revolutionize Facial Animation
iStorm writes, "I've been interested in computer animation for a long time and have recently started cracking down on my studies in an effort to eventually move myself from hobbyist to professional... then I find this article about Image Metrics, which can map an actor's emoting onto a generated face or onto the image of another actor, living or dead. How does a seasoned animator view this sort of push ahead in technology? If so much of the creative process is made so easy, where's the need for traditional animators spending exponentially larger amounts of time to create work of equal or lesser quality? How did animators view motion capture when it first appeared? Will there still be room for creativity if this tech comes to fruition?" The article doesn't say what kind of time or processing power Image Metrics's "high-fidelity, performance-driven facial animation" requires.
We did all our art in MacPaint. We only had the basics mind, a line tool, a square tool, but we didn't complain.
My roommate is a digital animator and if his comments are worth anything then Mo-Cap is not all it's cracked up to be. This new great thing may end up there, where it can map facial expression but does it in a way that isn't quite right looking to the human eye, thus requiring hours and hours of cleanup afterwards.
I think it'll be a while before the industry starts putting out photo realistic digital animations of people.
A blog about stuff.
In Soviet Russia, article writes YOU!
I doubt that this technique will knock animators or traditional animation out of business. Animation is art. Did the video camera kill painting? Did the internet kill reading?
Animation from an animator gives it style, and feeling just as much as an actor does. Just watch any old Disney cartoon if you want to see the flow of such animation.
How did painters view photographic technology when it first appeared?
Humans hold human characters to a higher standard than other CGI. It's part of the reason why Toy Story, Monsters, Inc., A Bug's Life, and Over the Hedge have focused mainly on non-human characters or a cartoon-like story. When a more "adult" story is tried, as with Final Fantasy, the technology still comes up short. It's a step in the right direction, but until you can't discriminate between a CGI actor and a real one, this isn't going to be used in "serious" movies.
None of these new techs are 100% plug in solutions, they often require a lot of personal time with someone who knows what they're doing. Further a lot of animation is fluid melding of one animation sequence to the next which can often be difficult to automate.
I don't see the face mapping tech being much more different then mo-cap just on a smaller level. If anything proceduaral synthesis will bring the biggest changes to animation, but you'll still need people to code even that.
Collector's Edition
Crappy acting will still be crappy acting. Just like the foley artist is still happily employed enhancing the audio soundtrack (either digitally or old fashined foot stomping). The animator will remain gainfully employed improving and enhancing the final product.
___________________________
Free iPods? Its legit and simple. 5 of my friends got theirs. Get yours here!
Didn't they use this (or maybe they were going to but never did) when the actor who played Dumbledore died? I thought i remembered reading that they were going to map the dead actors face onto the new actor?
Short answer: Polar Express. Just compare this movie to any Pixar feature and you know the answer.
I don't care how much processing power it takes, unless we are talking simulation on the level of some of the whole-world-weather simulations any additional processing will be a drop in the bucket compared to the current amount of time and processing power already devoted to any production quality animation.
This will revolutionize pornography--just think of all the degradation that can be simulated!
(Posted AC because I disgust myself.)
How does a seasoned animator view this sort of push ahead in technology? If so much of the creative process is made so easy, where's the need for traditional animators spending exponentially larger amounts of time to create work of equal or lesser quality?
Technology usually advances so that it is not only more advanced, but also more efficient. It's fairly obvious that Hollywood studios (just an example) would want cheap CGI, and since there's a need for this to happen, there's also someone working on making that happen.
A skilled animator shouldn't be worried, however. Creativity is hard to replace with software and someone will always have to create whatever's portraited. How it's done and how fast is a different question.
Full Tilt
...we hacked off the fingers of our enemies the Cro Magnon and painted in red with them on cave walls to show off our victories: truly DIGITal art! MacPaint was only black and white!
I've been doing 3D character animation for well over a decade, and I've also been exposed to automated facial animation systems including mocap (in many of it's various forms) over the years. I actually think mocap is not bad for certain applications, particularly whole body stuff like athletics. If you really want that golf swing to look like Tiger Woods in his video game, then mocapping him is a very valid option.
What it's not good at, however, is animating the face. People have been trained since birth to observe human faces and we're experts. It makes us very aware of anything that's unnatural. Only a human who innately understands the subtleties of human emotions can truly finesse facial animation so it looks pleasing to the human eye. An animator is just that type of person. We study facial expression, musculature and all sorts of things, then combine it with acting skills and artistic knowledge to make a result that's looks pleasing to the eye (or not.. depending on budgets and deadlines - and I suspect this technology will filter down to the low end productions that don't care as much about the final results)
We have algorithmetically generated art or literature that has to convince users' software filters that the users would be entertained by it?
I believe they did a lot of work with the polar express movie.
I also used to work above them, nice guys.
Here's a quote, usually attributed to the WWI German flying ace, Baron Von Richthofen:
"It's not the crate...it's the man inside the crate."
I'm gonna ask you to ponder this and extrapolate to the imagined quandary you propose. Also, I'm going to leave you with a bit of personal history:
I started in the graphic design business back in the early 70's, when a well-stocked "micro-studio" would set you back about around $50,000 (in 1974 dollars) for equipment, which included: a digital typesetter, process camera, film/paper photo processor, drafting table, waxer, light table...plus a few other lesser (though expensive) goodies. A decade later, inexpensive (relatively) personal computers with laser printers and scanners could be had for less than $10,000, essentially replacing my studio gear. Meaning every small business on the planet could suddenly be competing with me in the graphic design biz on some level. Predictably, a whole bunch of them tried. Did it put all the typographers/designers/pre-press craftsmen out of business? Well, it separated the wheat from the chaff, certainly, casting adrift the bottom 20% (subjective talent evaluation on my part) of the professional industry. It also produced an explosion of amazingly awful graphic design/typography, produced by folks whose accountants convinced them to attempt to save money by doing it themselves. However, those of us who actually had some skills/talent/Mojo actually thrived, selling our work by pitching the client on a comparison of our stuff to the examples of sub-par work that resulted from trying to replace talent with technology. Yes, I pitched a lot of FUD back then, showing a potential client the absolute worst examples of things produced by People Who Really Shouldn't Be Allowed to Touch Photoshop. Only...maybe it really wasn't really FUD. 'Cause when you objectively look at it, the good Baron's quote still rings true:
"It's not the crate...it's the man inside the crate."
All the computer programs in the world, along with all the hardware in the world, don't help if you don't got that Mojo to begin with. The tools are subservient to the talent, not the other way around. At least until someone develops a keyboard with a button that says "creativity."
* * * * *
Be like a postage stamp. Stick to one thing until you get there.
--Josh Billings
I've worked with 3D animation off-and-on for over 10 years, including professional movie studio work. MoCap was always, at best, 90% there.
This, however, impressed the hell out of me, especially the African Warrior. WOW!
Is it the end-all-and-be-all of digital animation? No, but it is generations ahead of things like Polar Express.
Just watch the video before making any judgements.
Learning HOW to think is more important than learning WHAT to think.
However, the real challenge still remains for the actors: generating a facial expression intentionally usually does not produce the same muscle contractions that spontaneous emotions do. Thats the whole difficulty with acting, you can't make your face do what you think happens when someone is angry, you have to get angry and let your face do its thing.
It's another tool.
There will be some things it is suitable for, and some things it's useless for. I can't see this having much use in the production of a show based around drawings, for instance!
Back during the production of "Snow White", Disney shot a lot of reference film. Some of the animators leaned heavily on this, essentially just rotoscoping the model and stylizing her a little into Snow White. Master animator Grim Natwick would refer to the first and last frames of his reference film, to make sure it hooked up properly with the adjoining scenes, and essentially ignored the rest.
Guess whose scenes had the most life in them?
For some purposes, the raw data out of this will be fine. For other, it's a starting point for an animator to go over, and possibly completely abandon.
egypt urnash minimal art.
Film at 11.
You better watch out, there may be dogs about . .
Yeah, the article is a little sparse on details. What kind of power does it take? Is the software for sale? What are the costs associated with production? The article did allude to a time savings. This seems to be a clone of stuff they've been doing in Japan for a few years.
"The mind works quicker than you think!"
They are making a CGI version of Beowulf. Let the slashbot flogging of the demised equine that is the "imagine a Beowulf cluster" meme begin.
www.eFax.com are spammers
Luxury! We would have killed to be able to use someone else's parts: we had to leave our own dead chalky bodies, generation after generation over thousands of years, to produce any art. Granted, back in the day art lasted longer, not like this newfangled "digital" stuff. Pah.
>If so much of the creative process is made so easy, where's the need for traditional animators
/anyone/ could make a pretty good looking web page. Did a lot of web page authors bite the dust then? Sure. But the ones who remained advanced their art - now they are masters not just of HTML but PHP, AJAX, JAVA, Flash, and a host of other cutting-edge web functionalities.
>spending exponentially larger amounts of time to create work of equal or lesser quality? How did animators
>view motion capture when it first appeared? Will there still be room for creativity if this tech comes to fruition?"
This sort of thing has always come along. For example, WYSIWYG applications like Front Page let people like me create web pages without knowing hardly any HTML. Suddenly
Computer Aided Drafting did the same thing to mechanical drafters who worked on drawing boards with pencil and paper.
That's kind of the point of technology - to make what were once difficult or tedious expenditures of effort become effortless. Talented people who specialized in those old efforts will have to move on to tackle new things that are still difficult. There's always a new cutting edge.
Steve
A work that expires before its copyright never enters the public domain and thus enjoys eternal copyright protection.
Most good animations exaggerate the motions of the characters to add life and energy. On screen, having everything turned up a notch above what it would be in the real world helps convey the message you're going for. And of course facial expressions are included in all of that. Using mocap only captures reality(or at least it tries to) and doesn't allow for any freedom to exaggerate things as the animator sees fit. And even if you wanted to start with mocap and build in some other motion from there, it makes it difficult to do so because of all the noisy data that it collects. Picking through that and cleaning it up so you can work with it can be more time-consuming than just doing it from scratch yourself.
So no, I don't think it's going to make such a big impact that animators will have to worry about keeping their jobs. Humans are actually good at some things!
So you used Corel's predecessor Coral? Sounds like luxury to me.
"Unheard of means only it's undreamed of yet,
Impossible means not yet done." ~~ Julia Ecklar
Thousands of p0rn "actresses" just lost their jobs.
I can't believe I'm the first person in this thread to realize this!
...following the principles of Heisenburger's Uncertain Cat...
Mapping from one human onto another is not that hard compared to what real animators have done.
How does a bunch of mops become an unstoppable force?
How do you make a lion comforting?
What makes a toy ballon menacing?
Maybe someday studios will realize that CG blows no matter how good it is-- it will never make a film "worth seeing". Granted, good CG brings people into the box office. That's probably all studios care about.
OTOH, I would rather see a nice CG recreation of Richard Harris as Albus Dumbledore than the guy they have now. The difference is so striking as to be disconcerting-- for a Potter fan, that is. Harris was the bomb.
This technology will never take your job. It will take the job of the Chinese animator who takes your job. The money saved in each instance will go to the executives and stockholders of the company. Luckily, in America, you will still have some options to keep a roof over your head. These are welfare and prison. This is the system being used for the displaced auto manufacturing employees in Detroit.
Thomas Pynchon explains it all here:
http://www.themodernword.com/pynchon/pynchon_essa
In an era when virtually anyone can buy a video camera, we don't find ourselves flooded with great documentaries and movies. Instead, there's a lot of OK stuff, a bunch of total crap, and a few outstanding new DPs and Directors - who suddenly get paid a bunch of money and get to use the REAL big tools.
Unfortunately, the fact that there are so many documenaries being made means that good material won't wait around for a Ken Burns or an Erol Morris do do a GOOD film.
The same thing has happened over and over from the days when people who were really great at setting display type with a waxer and an Xacto Knife were displaced when people with a Mac could do a really crappy job of it with a laser printer, only much faster.
In the end, the way to get noticed and paid well AFTER the revolution is to be top of the heap.
But you're going to have to compete with a bunch of high-schoolers using pirated software in their bedrooms, which means you're going to have to do a better job at adding value, better job at marketing, better job at solving problems (visual problems, the customer's real-world business problems, turn-around-time problems, come-through-in-a-pinch problems, etc) than the average kid.
Digital revolutions separate creators into Artists and Craftsmen. Artists have the vision and can deliver creatively no matter what the toolset - and broaden "toolset" to include a bunch of offshored animators bringing the artist's vision to life. Craftsmen find themselves quite good at tools that are no longer used.
If you're a Craftsman, you either need to hurry up and educate yourself into something else the unwashed masses won't be able to do for a year or two, or work on your ability to add value as a problem-solver, or a mentor and educator of new young Craftsmen and Artists.
I used to be a Craftsman. A Multi-Image animator and programmer (like This Guy (not me...). Then I got a look at Adobe Photoshop. "Yeesh...I'll be out of a job pretty quick!"
Been a craftsman a few times, actually. Now make my living trying to help people solve their problems.
Eventually everything will be done by computers and robots. Why deny the inevitable? Just sit back and enjoy, until they take over, at which point we're screwed anyway.
Say... Keanu Reeves. Since he's only got one facial expression, all you need is a camera and... well, that's it.
This sig isn't original enough, it's time to come up with something witty...
Wouldn't it be cool to make new episodes of Star Trek TOS using this technology? If you coupled it with voice synthesis, you could have Bones and Scotty right in the mix. Maybe the producers could save enough on actor's salaries to pay to get some writers!
I believe a Botox(TM) filter was applied in the first image ("Emoting by Llana Rogel, an actress, is translated into a computer image.") Either that or Llana always has bug eyes and deep wrinkles in her forehead!
Like Star Wars? The Matrix? Lord of the Rings?
--Edward Dassmesser
This technology simply adds more virtual mo-cap nodes to an actor's face. That is the only thing new here - insead of the previous' technology (Polar Express et. al.) with hundreds of sensors, this simulates thousands or more. It is still mo-cap though!!!
Quality animation REQUIRES a skilled animator's touch - the more these companies try to create animation without the artist, the further they get from quality art. Look at how Pixar can make nearly abstract objects and characters emote, without any mo-cap.
The future of animation high-art will be the joining of animation artists and these tools, not some autonomous machine putting Marilyn monroe's face onto an actress scrubbing a toilet in a commercial for Tidy-Bowl.
One reason why animation that doesn't use an actor's work may persist is that it won't run into the licensing fees, or whatever they'll be calling them in the brave new world. I'm sure in-demand actors will charge suitably exorbitant rates for the use of their emoting skills. Or, more likely, their names.
Interesting, the CGI product "Zbrush" uses the same image on their website. Well it looks very much the same at least.
g /overview.php
http://www.pixologic.com/zbrush/zbrush-is-paintin
I guess they used zbrush to do the texturing and modelling and then this other product to animate it? Anyone know?
My Dad, an Amiga buff up to the day of his death, always said that we would know computer animation was truly mature when someone could make a new John Wayne movie that would be indistinguishable from an original. Sounds like someone might be able to pull it off with this technology.
Actually, there's nothing new or revolutionary about this. Eyetronics's LiquidFaces tool was capable of doing these things over 3 years ago. See: http://www.eyetronics.com/
The purpose for making an animated movie in the first place is generally NOT to create something that is difficult or impossible to tell if it is real or not. The value of animation is to be able to go outside the realm of reality. Looking back at recent history, (e.g. Southpark, the Simpsons), often the most successful animation projects have some of the least life-like appearance. There will always be a need for creative artists. The tools just help with the grunge work (tweening, etc.).
I first started attending SIGGRAPH conventions in 1984 and attended every year until (and including) 1998. In all those years, the only event I never missed was the film show.
... Pixar. What people consistently seem to forget is that good storytelling with characters we care about, done technically well, with at least a little bit of humor, leads to the films we remember best.
... ... technology in the service of storytelling, and not the other way around.
:: SI
In all that time there were several kinds of films that wowed audiences without fail:
1) Technical tour-de-forces (in 84 I think it was "Long Ray's Journey into Light" rendered using a rendering algorithm that used unused cycles (some 10,000 CPU hours IIRC) on networked Apollo Domain workstations).
2) Interactive experiences (imagine an audience of 3000 people playing Pong, thanks to Loren Carpenter and friends). Maybe you had to be there.
3) Humorous story lines.
4) Great storytelling.
The best films combined elements of 1), 3), and 4 and the masters of this were
Remember the bathos of Luxo Junior? Who would have thought that a little lamp could display emotion? Or a unicycle? What about the snowman in the snowglobe "in love" with the beach babe in her sandglobe? There are dozens of other examples I can mention and the common theme is
Technology will continue its inexorable march "forward" which is neither good nor bad in itself. What is "good" or "bad" is/are the uses to which technologies are put. It's getting to the point where it's difficult to tell, from a distance and if you're not paying close attention, whether a person in a game or movie is a live actor or a digital actor or even a digitally enhanced live actor. But it doesn't really matter if the viewer can't engage/identify with the actor -- real or digital.
This is a step up from Polar Express, but it looks like we need another step or two before it's good enough. Heck, Gollum didn't have that "slow motion" problem that this seems to have. Then again, the clip of Fred and Ethel looked pretty good.
-- Boycott Shell
Yeah, what if they use facial resemblance (just different enough to avoid lawsuit)to famous actress or models.
I didn't see the video, but the screenshot they're showing in the article looks like ass. I'm studying 3d animation and a few things are okay, such as the mouth shape, the jaw, and the pressing inward cheeks. But the eyes and eyebrows are terrible. Just look how the eyebrows on the 3d model don't curve outward from the eyes, the eyes are also just the standard shapes instead of exagerated larger (lower and upper eyelids should be pulling open further). Plus where's the folds in the skin for the brow? It's also missing any musculature under the eye. Another thing is the actress' left eyebrow (right on the picture) is slightly higher than her right one, which doesn't show on the mocap screenshot. It looks like she's saying Oh, but with no enthusiasm. I don't know if this was a limitation of the model, but it's got a LONG ways to go to match anything done by a good animator. For a good reference to facial animation, compair Polar Express to Golem from LOTR. Golem was traditionally animated and the Polar express characters were mo-capped. This may be a step up from polar express, but nothing beats the choices and exagerations of a good animator.
Stepping aside from animation for film, what about the use of this technology as an interface for transfering fine facial details into a virtual space? It would be interesting to write the interpreter/translator between this technology and online avatars, both human and non human. And yes, I am a furry. Thinking about seeing a smile on my face reflected in a canine ear and tail "smile" in second life makes me happy..... Rowanyote
How did painters view photographic technology when it first appeared?
Once people really embraced photography, it was a great thing for the art world, because painters were no longer burdened with the expectectation of reproducing reality. This freedom paved the way for abstract expressionism and dada.
The theory of relativity doesn't work right in Arkansas.