Believe it or not, GTA 5 He has been with us for nearly eight years. However, from the arrival of the PC version, in 2015, the game became a creative tool for many. Moderates. In general, these modifications focused on giving More realistic visual appearance, But you can be sure no suggestion was as surprising as the one you will know today.
Intel Intelligent Systems Lab, California’s internal team testing AI solutions GTA 5 To show the progress of its technology. The project, as they explain, basically consists of Realistic Image Enhancement. In the event that GTA 5, Whose graphics aspire to present a “realistic” hypothetical scenario, which artificial intelligence is aiming for Modify photos to make them look more natural. In other words: make it more realistic.
Now, we say “Tire” because Intel AI does its job in real time. he is called, Frame side frame. It is for this reason that some minor visual discrepancies can be observed. Despite the above, the end result is simply amazing. We never had a chance to see GTA 5 -Or any other country Grand Theft Auto– With this level of realism. You can check it yourself below:
Intel notes that its technology is too It is based on the graphics engine GTA 5Because it provides the basic information that an artificial intelligence requires. For example, the depth in relation to the trigger camera, the type of surface material, and of course the illumination data. Once this information is obtained, it is processed by Prof. Convolutional nerve red To apply photorealistic image.
This neural network makes comparison in record time with images from the real world. In this way, it determines the type of photorealistic detail most appropriate to apply to the virtual scene of GTA 5. Of course, Artificial intelligence You need an image database Huge for reference. This is where you play Cityscapes, Which is a bank of street and vehicle photography in Germany.
While the experience is impressive, video games are unlikely to take advantage of it anytime soon. Reason? Requires a computer with enormous potential. However, it gives us a good idea How does artificial intelligence continue to advance in image processing.