'

Intel makes GTA V Photorealistic using Machine Learning

Could AI enhancement deliver the future of gaming realism?

Intel makes GTA V Photorealistic using Machine Learning

Intel makes GTA V Photorealistic using Machine Learning

Realism has long been the visual target of AAA game developers, a graphics standard that will allow gamers to fully immerse themselves within digital game worlds. While photorealistic images can be rendered, achieving that quality standard is practically impossible at high resolutions/framerates, making photorealistic gaming practically impossible.      

Grand Theft Auto V delivered incredibly visuals at launch, which only became more impressive as the game launched on PC and newer console platforms. Now, a team over at Intel Labs has decided to take the game to the next level with an "Enhancing Photorealism Enhancement" mod, which uses machine learning to make the game much more realistic. The video below showcases their work. 

Intel's methods utilise an image enhancement network to transform GTA V's visuals, though the company's enhancement method is a lot more complicated than image enhancement/upscaling. Intel snoops at GTA V's G-buffers to look at important details like material properties, vehicle shapes, lighting buffers and distance buffers to allow their neural network to produce accurate results.

While Intel's results are not perfect, their video demo highlights that Neural Networks can be used to enhance the visuals of modern games. Intel's mod significantly improved GTA V's vehicle rendering, though Intel's technology does remove much of GTA V's artistic character and visual style in the process. You can look at more detailed comparisons here, many of which highlight how this technology harms GTA V's visuals in many scenes. In many cases, artistry trumps AI realism. 


   We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The network is trained via a novel adversarial objective, which provides strong supervision at multiple perceptual levels. We analyze scene layout distributions in commonly used datasets and find that they differ in important ways.

We hypothesize that this is one of the causes of strong artifacts that can be observed in the results of many prior methods. To address this we propose a new strategy for sampling image patches during training. We also introduce multiple architectural improvements in the deep network modules used for photorealism enhancement.

We confirm the benefits of our contributions in controlled experiments and report substantial gains in stability and realism in comparison to recent image-to-image translation methods and a variety of other baselines.


You can join the discussion on Intel's Machine Learning making GTA V more realistic on the OC3D Forums

«Prev 1 Next»

Most Recent Comments

17-05-2021, 19:28:23

Dicehunter
I know it won't happen but it would be great if Intel released a full AI modded texture/lighting pack for GTAV.Quote

17-05-2021, 19:58:19

KingNosser
Pretty impresive for Intel, but unless it comes to the public it's imho a wasted effort other than oh we have a nice tech demo, sure they will have learned something but no real point learning if you don't put it to use.Quote

17-05-2021, 20:46:19

ImprovizoR
It's a pretty impressive proof of concept, and the potential implications are astounding.


Think about this, for instance. Rockstar goes around taking a lot of photos and videos of cities in order to create the fictional version. Theoretically, they could partner-up with Intel and use this method during the development of GTA VI in order to make it more photorealistic. Same goes for other devs.Quote

17-05-2021, 23:46:40

Dicehunter
Quote:
Originally Posted by ImprovizoR View Post
It's a pretty impressive proof of concept, and the potential implications are astounding.


Think about this, for instance. Rockstar goes around taking a lot of photos and videos of cities in order to create the fictional version. Theoretically, they could partner-up with Intel and use this method during the development of GTA VI in order to make it more photorealistic. Same goes for other devs.

This likely won't be used for anything that we can get our hands on, Same with Nvidia, They've showcased some really cool graphical tech over the years that simulates fur, Fire, Water etc... and it could be used in games, Is it ? Nope it's unused and forgotten.Quote

18-05-2021, 00:01:06

tgrech
Quote:
Originally Posted by Dicehunter View Post
This likely won't be used for anything that we can get our hands on, Same with Nvidia, They've showcased some really cool graphical tech over the years that simulates fur, Fire, Water etc... and it could be used in games, Is it ? Nope it's unused and forgotten.
To be fair, really detailed environmental or character demo tech often looks nice and is easy to do for pre-recorded footage, but is usually a pain to get working in realtime while often not being worth the performance penalties in motion

With this, the performance penalty on AI accelerated hardware should be pretty minimal, and fairly flat across the board, while integration could be somewhat tacked on after the fact.

The potentially to use this to create multiple "themes" for a game- Dark, colourful, realistic, ect, or say historical-footage themed filters, is very interesting imo, particularly for say racing or simulator games where artistic styling isn't an intrinsic aspect of the game.

And with something like this, maybe we don't really even need official support, it seems pretty mod-friendlyQuote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.