Believe it or not, GTA 5 has been with us for almost eight years. However, it was from the arrival of its PC version, in 2015, that the game became a creativity tool for many modders. Generally, these modifications have focused on giving a more realistic visual appearance, but you can be sure that no proposal has been as surprising as the one you will know today.
Intel Intelligent Systems Lab, the internal team of the Californian company that experiments with artificial intelligence solutions, used GTA 5 to show the advancement of its technology. The project, as they explain, basically consists of enhance photorealism. In the case of GTA 5, whose graphics aspire to display a “realistic” virtual scenario, artificial intelligence aims to modify images to make them look more natural. In other words: make it more real.
Now, we say “images” because Intel AI does its work in real time. Namely, frame by frame. It is for this reason that some minimal visual inconsistencies can be observed. Despite the above, the end result is simply spectacular. We have never had the opportunity to see GTA 5 – or any other Grand Theft Auto – with this level of realism. You can check it yourself below:
Intel notes that its technology also is supported by the graphics engine of GTA 5as it provides essential information that AI requires. For example, the depth relative to the player’s camera, the type of surface materials and, of course, lighting data. Once this information is obtained, it is processed through a convolutional neural network to apply photorealism.
This neural network makes a comparison in record time with images of the real world. In this way it identifies what kind of photorealistic details are the most suitable to apply to the virtual stage of GTA 5. Of course, the AI you need an image database huge for reference. This is where it comes into play Cityscapes, a bank of photographs of streets and vehicles in Germany.
While the experiment is impressive, video games are unlikely to take advantage of it anytime soon. The reason? It requires a computer with enormous potential. However, it gives us a good idea how artificial intelligence continues to advance in image processing.