Watch GTA 5 Morph Into A Photorealistic Sim With Machine Learning Sorcery From Intel
Some people are concerned about games like GTA 5 affecting peoples' behavior in real life
, but what if those games actually looked
like real life? Researchers at Intel Labs may have figured out how to do just that using machine learning to make rendered footage look photorealistic. This technology could just bring gaming
into a new era if it is used in the wild.
Since the dawn of video games, people have been trying to make them as realistic as possible to achieve the most immersive experience. PC and console hardware has grown over time as well, which nicely complements this goal. Take, for example, the Tomb Raider games, the original of which looks to us more like a Cubism art piece versus what we have now. It seems that things have somewhat stagnated, though, as Moore’s Law can only take you so far on hardware, and the equivalent law in software can only go so far as well. However, Intel
Labs researchers may have found a way to circumvent any traditional notion of what a game looks like by using machine learning techniques.
Tomb Raider I Released In 1996
The Intel Labs team’s project abstract
describes how they can enhance synthetic images through a convolutional network, which is a type of deep neural network
. This neural network was trained using the rendered images from the game alongside intermediate rendering buffers (G-Buffers), which “provide information on the geometry, materials, and lighting in the scene.” The G-Buffered are processed and used as input for the image enhancement network “where they are used to modulate image features.” While there is a lot more that goes into it, this work culminates in the footage you see below from GTA 5
If we did not know it was from GTA 5, it would be hard to tell that it was not real. Of course, some minor issues appear, such as license plates becoming a blurry mess, but that pales compared to the rest of the video.
Besides, are you looking at license plates while driving around in GTA? In any case, this sort of technology is wild, and we cannot wait to see where it goes. If you are as excited as we are, let us know what you think about it in the comments below.