(Pocket-lint) - GTA V has been modded a few times over the years since it launched, but even the best mods don t make it look as realistic as the work Intel has done with machine learning.
Through a machine learning project that s being carried out by a team at Intel Labs, the game has been visually overhauled in truly impressive ways.
This project, known as Enhancing Photorealism Enhancement has taken scenes from Grand Theft Auto and transformed the visuals to make them more realistic and the results are staggering.
As you ll see from the clips and images, the work by Stephan R. Richter, Hassan Abu Alhaija and Vladlen Kolten has overhauled the visuals with more realistic washed-out lighting, convincing real-world styled reflections and much more besides.
Researchers at Intel labs have been looking at enhancing the realism of synthetic images. Stephan R. Richter, Hassan Abu Alhaija, and Vladlen Kolten recently published a research paper and accompanying demo video showing a new ML-based technique in action - changing the great but obviously synthetic graphics in GTA V to a much more realistic and photoreal experience.
The new ML rendering method is described as enhancing the in-game graphics by leveraging a convolutional network that has been trained on the Cityscapes dataset . The results are clearly different and appealing in a real-world way. However, it is explained that the Cityscapes dataset isn t derived from driving around Southern California, but mostly from driving around cities in Germany with an automotive grade camera. One unintended side effect of using the German data is that the landscapes in San Andreas become greener, and the roads smoother and less pot-holed. Other effects like the shading and lighting of cars a
Researchers at Intel labs have been looking at enhancing the realism of synthetic images. Stephan R. Richter, Hassan Abu Alhaija, and Vladlen Kolten recently published a research paper and accompanying demo video showing a new ML-based technique in action - changing the great but obviously synthetic graphics in GTA V to a much more realistic and photoreal experience.
The new ML rendering method is described as enhancing the in-game graphics by leveraging a convolutional network that has been trained on the Cityscapes dataset . The results are clearly different and appealing in a real-world way. However, it is explained that the Cityscapes dataset isn t derived from driving around Southern California, but mostly from driving around cities in Germany with an automotive grade camera. One unintended side effect of using the German data is that the landscapes in San Andreas become greener, and the roads smoother and less pot-holed. Other effects like the shading and lighting of cars a
Intel is using machine learning to make GTA V look incredibly realistic
Imagine playing the game inside a photo
Share this story
One of the more impressive aspects of
Grand Theft Auto V is how closely the game’s San Andreas approximates real-life Los Angeles and Southern California, but a new machine learning project from Intel Labs called “Enhancing Photorealism Enhancement” might push it toward photorealism (via
).
Putting the game through the processes researchers Stephan R. Richter, Hassan Abu Alhaija, and Vladlen Kolten created produces a surprising result: a visual look that has unmistakable similarities to the kinds of photos you might casually take through the smudged front window of your car. You have to see it in motion to really appreciate it, but the combination of slightly washed-out lighting, smoother pavement, and believably reflective cars just sells the fact you’re looking out at the real street from a real dashboard, even if it’s all virtual.