Automatic image generators from words have become the new fashion on the internet, however, this is only part of the iceberg and that is why we have decided to look to the horizon to show you how this type of technology will completely change the way to produce your favorite games, whatever the platform we are talking about. And not only in the field of games, but in other fields. Let’s see, therefore, how AI will be used to improve the level of detail of three-dimensional scenes
The term Neural Rendering At the moment it is unknown by the masses, but over time it will become more important. And it is that behind this name is the concept of using the benefits of artificial intelligence for the generation of graphics. Either through computer vision or Deep Learning. In recent years we have seen image reconstructions at a higher resolution or with a greater color range, but other utilities are beginning to be seen, such as being able to predict lighting in a 3D environment to be able to apply ray tracing or in the case that concerns us to be able to create elements of lesser detail in an automated way.
Level of detail in 3D graphics and AI
You are playing a racing game and sadly the rival car has just overtaken yours in the distance and it is showing less and less detail. It looks like the same model to us, but there are actually several that are loaded into memory and that have had to be modeled by an artist during the design phase. Because the visual fidelity is lost, those that represent the car at the furthest point end up using fewer vertices and, therefore, fewer polygons.
Well, one of the things that the games are going to benefit from will be the automatic creation of models with a lower level of detail than the originalsimply through the use of computer vision of the most detailed model. That is, through simple observation of the model, the AI will be able to create a chord model at a shorter distance that can be used as in-game modeling. What’s more, it will be able to include the way to generate it procedurally, which means that, instead of containing the graphic data of the model, what it will have is the information to generate it automatically with less detail and using different styles for it.
Like current generators, but with vertices instead of pixels
The concept is the same used in the AI image generators that have become fashionable and is based on the idea that an algorithm is developed that allows you to learn to observe and then reproduce it. It has been tested with two-dimensional images, but keep in mind that we will also see it in 3D models made with vertices.
Obviously, the AI is not totally foolproof and has limited reproducibility and is often buggy. Professionals will continue to be necessary to polish and give the correct shape and give artistic personality to the work. However, it will serve to get rid of the tedious work. Not to mention that it will speed up design times and not just in games. Who tells you that the industrial design of your future car is not going to be generated in part by an AI?
Generation of 3D worlds through photography
Another of the applications of all this, although it is rather a combination of everything we have been seeing and that is going to be revolutionary in the mass market, is the fact that through a photograph a three-dimensional world can be generated. That is to say, that Artificial Intelligence after seeing a photo reconstructs it as a 3D model with textures and everything.
This, which in principle may not be useful and is no longer a simple curiosity, has very large applications in the face of simulation and what are called virtual twins. Which are computerized versions of real environments used in simulations. What is the ideal flow of people to avoid collapses and misfortunes at a concert? Which route is the most efficient to build a new highway? All this will save the time of having to build the scene in 3D, just one or more photos will be enough.
Even after the destruction of a neighborhood or a building, it will be possible to rebuild it as it was originally or to carry out historical reconstructions. How about a virtual trip to your favorite city at a specific time? Well, all this is possible thanks to the use of artificial intelligence such as GANverse 3D.
