Where does the computer animation industry go: how graphics changed and why is it a big deal (part 2)

The short answer is: A lot. The long answer is: Also, a lot. The longer answer: please, read this article. Also, don’t forget about a part 1. 

Computer animation has come a long way in recent years, and not everyone is keeping up. This is largely due to the advances made in artificial intelligence (AI) and machine learning. These accelerators are making us to catch the breath in our pursuit of changes. But we did a good job chasing them.

Historically, creating believable and realistic animations was a time-consuming and painstaking process. It required hand-drawing each frame of the animation or at least total involvement in the process of a considerable number of professionals. Professionals, that can do something more creative and unique.

Now, thanks to AI, computer animation has become much more realistic and lifelike. AI-powered computer animation software can automatically generate realistic animations from a few seconds of footage. But that’s not the point: we are aiming to look at the cases that explain more about the changes in computer animation graphics. Are you with us?

Graphics plays an important role in presenting images and videos. With the fast pace of new technologies and trends, graphics have changed a lot throughout the years. In the recent past that many of us are able to remember, graphics were only used for static images.

However, nowadays, things had changed drastically. Graphics software is readily available and able to create dynamic images. This change has made the field of graphics more interesting and easy to explore. Thanks to these advances, designers and animators are now able to create unique graphics within a few steps.

To understand the vastness of appliance of graphic you just have to keep in mind that it is a major part of representations in biology, computational physics, computer-aided design, computer simulation, digital art, education, graphic design, infographics, information visualization, scientific visualization, and video games.

In this article, we are going to take a closer look at the changes that are happening to the whole computer animation graphic industry and will direct your attention to specific cases. Get ready.

Computer-Generated Imagery as the core of changes

Computer-Generated Imagery, well known to all of us as CGI, is a great part of computer animation graphics. Its function is to create animated visual content with computer software, including still pictures.

When we are talking about Computer-Generated Imagery, we usually refer to the 3D computer graphics that we know by the characters, scenes, and a bunch of other effects we used to.

But this technology is not prior to super expensive animation we used to see in cinema. Not at all. We have also seen it in advertising, virtual reality, and even art. As long as this is a major part of computer animation graphics we have been talking about, we can’t miss it in this article.

CGI is created using different approaches:

• 2D pixel-based image editors can produce vector shapes.
• 3D graphics software can generate a variety of shapes.
• 3D software simulate the light and its relation to the other objects like surfaces, for instance.

This one of the main areas where animation has been improved. Not only because major animation studios like Disney are use it to create their movies, but because it affects the whole animation continuum, so to say. The other fields depending on computer generated imagery as well.

How exactly is it being improved

Computer animation graphics always changing, and it is happening right in front of us. A lot of researches works to change it at this moment. But what is the main approach to providing these changes? You probably already guessed. It is mostly AI trainings.

Recently, researchers at Dartmouth have developed software techniques that make lighting in computer-generated images more lifelike and real. The new technique, called reservoir-based spatio-temporal importance resampling, creates realistic lighting by using artificial light sources.

The new technique can be integrated into the design of future games and video.

Comment from Wojciech J.

“Over the last decade, ray tracing has dramatically increased the realism and visual richness of computer-generated images in movies, where producing just a single frame can take hours. Our papers describe two very different approaches for bringing realistic ray-traced lighting to the constraints of real time graphics.”

The artificial intelligence works 24/7, going through millions of trials to learn how to simulate different moves of the characters and how to come up with the image that is lifelike.

This is a major change in computer graphics and its quality: the machine is learning all these things to grant us a perfect image flow.

Since artificial intelligence is able to learn in ways that humans simply can’t, it is advantageous to use it.

“This is actually a pretty big leap from what has been done with deep learning and animation. In the past, a lot of work has gone into simulating natural motions, but these physics-based methods tend to be very specialized; they’re not general methods that can handle a large variety of skills. We developed more capable agents that behave naturally. If you compare our results to motion-capture recorded from humans, we are getting to the point where it is pretty difficult to distinguish the two, to tell what is simulation and what is real. We’re moving toward a virtual stuntman.”

UC Berkeley graduate student Xue Bin “Jason” Peng, involved in one of the projects. 

Making computer animation more flexible and acrobatic to achieve realistic features

Training artificial intelligence have only one aim — to make it learn how to make the images and moves as realistic as possible. If in the past you could easily tell that the movements of characters are a bit peculiar, cartoon-like, now the technology make it impossible to feel the difference.

Comment from Parris Egbert

“If the animator invests the time to run a simulation then the director looks at it and says it’s not quite right, he or she has to start from scratch, change some parameters and run the entire simulation again. That process will be repeated as many times as it takes for the director to approve it.”

If you think about, one of the reasons why computer animation is changing so fast, you will probably understand that our expectations are push it is hard. We want to make it as real as possible, or at least we want to have the option to make it as realistic as we see something in everyday life.

For example, one of the projects is trying to make a water look more realistic. It does require the changes of the graphic.

A team of computer science professors at BYU created a method to quickly resize animations of fluids and called “fluid carving.” This is what helps them edit a 4-dimensional video “which is a 3-dimensional image spread out over time, in the same way”. The function is a very complex piece even though it might sound as the easy thing. It took the group almost a year to finalize the whole idea.

https://giphy.com/gifs/disneystudios-disney-frozen-2-5dY4XX5ZCvjZ3AENUu

via GIPHY

This is just another example that shows how graphics is changed by requirements we have to images. Such projects are innumerable, and to track all of them is impossible. However, we can’t miss what they are coming up with, and, eventually, see the outcomes of their works in the newly created animation.

How AI captures what we can’t

Another reason for these major we are talking about is that AI can recognize and track human movement much more accurately than humans can. AI can also generate realistic textures and lighting effects. Overall, AI has made computer animation much more realistic and lifelike. It has also made it much easier and faster to create animations, and we needed that, a lot.

By working on such details as mouth movements, researches make it really possible to recreate precise effects we see in real life. A number of algorithms and approaches have been used in order to create realistic mouth animation in for video games, commercial animations, and other types of media. In order to capture the features and expression of speaking mouth, the developers and researches special modelling techniques.

Also, we see first AI experiments in creating entire animation movies. For example, the artist uses a set of algorithms of Stable Diffusion to produce tanimation. The movie is a result of collaboration between the artist, AI, and Daz3D, Unreal Engine, Photoshop, After Effects, and Premiere.

The whole idea besides capturing the movements of the human body is easy to explain differently. The thing is that not only the work is in the direction has been done — fitness app also trying to catch movements for their own development and better customer experience. It is also, as you understand, requires animation.

Summary

Comment from Ofir Zuk

“Our focus is to aid computer vision teams and accelerate their development of human-centric computer vision tasks. We are specifically trying to solve and help understand the interconnection between humans and their interaction with surrounding environments. We call it human in context.”

What else? Well, it seems that along with imagery, animation is going further, adding the elements that enhances our feeling of reality.

“There’s been a Holy Grail in computing of being able to simulate reality for humans. We can animate scenes and render them visually with physics and computer graphics, but, as for sounds, they are usually made up. Currently there exists no way to generate realistic synchronized sounds for complex animated content, such as splashing water or colliding objects, automatically. This fills that void.”

Doug James, professor of computer science at Stanford University.

Even though graphics is not only restricted to computer field – it is also a part of photographs, diagrams, typography, geometric designs, maps, engineering drawings, or other images – but it is on computer animation graphics these changes are most visible.

Animators and designers use new and advanced technologies, methodologies and number of different algorithms to deliver an image that would amaze us and please the eye. And we have a strong feeling that despite the fact that we come so far, it is actually only the beginning.