WHY THIS MATTERS IN BRIEF
Up until now if a games developer wanted to change the look and style of a game they’d have to crack open its code, but now they can just apply a style in real time without having to.
Interested in the Exponential Future? Connect, download a free E-Book, watch a keynote, or browse my blog.
At the start of the year Google unveiled their cloud based game streaming service Stadia that hopes to bring gaming “to the next two billion people” wherever they are and on whatever device they want to use. Now, a few months down the line from that announcement they’ve unveiled a new funky development tool that will let game developers change the style and feel of their games in real time using little more than a single image and some Artificial Intelligence (AI) Machine Learning trickery, and they’ve named their new impressive tool, a demo of which you can see below, Style Transfer ML.
The idea behind Style Transfer ML is to make it easier for a game developer to apply an art style to an entire video game in a shorter period of time. The technology behind this is nothing new, but creating frame-by-frame animations within something such as a game all in real-time is nothing short of amazing.
Applying a 2D image to dynamic game play in real time
Google showed off their new tool in a Stadia blog post where they used it to apply a whole variety of new styles to a “greybox game.”
As the company explains: “Translating from an illustrated, two-dimensional piece of concept art into a fully realized game environment would ordinarily require custom texture painting, modelling, material crafting, lighting, and tuning. Real-time artistic style transfer potentially allows developers to go straight from looking at a concept to testing it in a live, interactive game environment. This might enable rapid iteration of a video game’s art style. Real-time execution of artistic style transfer also opens up new forms of video game interaction, including the shifting of visual styles during gameplay, individually customized artistic styles (personalization by the player), styles generated through user generated content (turn a drawing into rendered game art).”
[…] players, either. They promised us that games would play better on Stadia thanks to innovations like negative latency, AI, and machine learning. Again, promises of what could be, but nothing tangible or valuable […]
[…] uns versichert, dass Spiele auf Stadia sicherlich besser laufen würden, dank Innovationen wie negative Latenz, KI und auch maschinelles Lernen . Noch einmal, Zusicherungen dessen, was sein könnte, aber heute absolut nichts Greifbares oder […]