Life-like Gaming is Now Possible (Thanks to A.I.)

hi welcome to another cold fusion for you right now were at the start of an AI revolution you might hear people talking about AI threatening to take over jobs or doing stranger things like playing games like the board game go or Starcraft 2 but most people think that the arts and creative fields are outside AIS capabilities but this is up for debate a method called style transfer which.

usually entails taking the artistic style of a famous painter and transferring it onto a still image or even video has been achieved in the instances of still images the AI managed to fool 39% of art historians but what about creative AI doing something actually useful that could potentially save millions of dollars and improve an entire industry by leaps and bounds well this is happening a iess creativeness is now moving into the 3d visual arts potentially.

revolutionising video game production and graphics in this video well take a look at that and some other ways that the AI revolution is seeping into gaming you are watching ColdFusion TV since crisis from 2007 we havent really seen a major step forward in the visual quality of games yes they do look marginally better but it hasnt been an incredible leap forward this is about to change with something called a real-time ray tracing ray tracing without going into detail simulates the way light reflects and interacts with surfaces in the real world it does this by.

calculating the past that each ray of light would take in a scene ray tracing gives their elements of realism thats missing from todays games current games fake the effect of lifes behavior ray tracing simulates it its why Pixar movies look so different to a playable video game so this sounds good but the problem with ray tracing is that its very computationally expensive traditionally you need a big farm of graphics processors to produce results.

its definitely something suited to pre-rendered CGI movies and not real-time video games this all changed with NVIDIA Tsar TX graphics card with this real-time ray tracing is now possible this was achieved by specialized Hardware tailored for AI doing all of the heavy lifting the hardware is called ng X and it uses processes that are custom-built for matrix multiplication the mathematical heart and soul of modern AI with this the hardware enabled AI learns how light should bounce and simulates this it puts the paths of light where it thinks that.

should go the result is a realistic real-time image that for the first time comes down to the consumer level in 2019 ray tracing was integrated into Unreal Engine and now the technology can be used in very general cases to highlight just how much of a difference ray tracing makes heres a video by digital foundry showing minecraft modded with ray tracing minecraft is probably one of the worst looking games graphics wise but with ray-tracing it actually looks pretty realistic it doesnt end there though heres some real-time ray tracing scenes of a BMW.

juxtaposed with a shot of a real BMW [Applause] and rounding up here some other general examples of ray-tracing [Applause] [Applause] in the future this kind of video game quality will become standard [Applause] ai is also being used to create more realistic smoke and fluid simulations without the heavy processing that goes with it not only this but a research team at the university of edinburgh developed a machine learning system that is trained by watching motion capture clips showing various kinds of movement the system correspondingly then generates an animation this can be anything from a job to a run to hopping.

over an object to train our system we first cut through several long sequences of raw locomotion data at a variety of speeds facing directions and turning angles we also capture motion of stepping climbing and running over obstacles placed in the capture studio by giving us input the height of the terrain under the trajectory our character can adapt to rough terrain climbing balancing and jumping were required either using the gamepad or the environment we can get the character to.

crouch or move under obstacles it can additionally be forced into certain environments such that the desired motion is performed as shown walking over this beam in summary we present a new method of character control using a faes function neural network which can produce high-quality motion complex controlled tasks such as walking over rough terrain its fast compact stable and can learn.

from a large amount of data this takes the tedious work out of creating realistic movements of videogame characters in a free market whatever is cheaper faster and better will eventually become the standard the same applies to the gaming industry less style of game development its no secret that the cost of video games is going up but why is this once upon a time major games could be.

made with a small number of people this is because the assets or 3d components of the game was simple as time went on games strove to chase realism as this happened the components of the game became ever more complex its gotten to the point where it now takes a large team and the budget of a blockbuster movie to complete a major video game title Andrew price a video game artist conducted a talk at a blender conference in 2018 in the talk he produced a realistic estimate of how exactly things.

get so expensive so one detailed 3d building can take 22 hours to create 12 hours for the modeling stage and another 10 hours for the texturing process but the job is far from complete at this stage theres usually a revision of two to four times depending on whats needed within the games story the end process can be 44 to 88 hours of work just for a single building within a game at a wage of $60 per hour the average cost of one building is around $4,000 when you add up all the costs it becomes.

comical this single scene cost around $200,000 a full game would have no problem reaching the hundreds of millions of dollars mark working this way the expense is largely due to the process of designing the elements in the game currently video game artists use a static flow from the design of the element to the output that is the completed product is a one-to-one ratio to create a new 3d asset be it a car or building requires the designer to start almost completely scratch this is where AI comes in AI particularly new your networks a suited.

to a kind of workflow called procedural content generation this is basically where a neural network is trained to create realistic buildings cars or audio from vast volumes of data over time it learns what looks good and whats realistic with procedural content generation a game designer simply has to type in certain parameters such as a building should be of a certain type.

have X amount of windows and B of a height within a certain range once given these parameters the AI then generates a whole bunch of options and the designer simply has to pick one with little or no modification and this is where the advantage comes in if another 3d asset is needed instead of starting from scratch the designer simply puts in the fur a meters and the AI generates it again countless hours are saved even though to train the AI in the first.

place might take a while the same process can be done for natural landscapes or even video game characters themselves to top things off what if an AI could create a whole video game by itself well of course this has already been done just recently researchers at Georgia Tech took things our step forward by using a general adversarial network a type of neural network which weve covered extensively before on this.

channel this network was deployed to invent new games in their paper they use video game levels from already developed games as inputs and then converted them into an output that lays out environments objects and rules for the new game this particular system learned from two games Super Mario Brothers and Kirbys Adventure and the output turned out to be a game similar to Megaman.

so I think this video shines a light on a side of AI that isnt really talked about AI being not only creative but actually practically useful combining all of the elements that youve seen here its clear to see that AI is going to have a drastic effect on the future of videogames theyll look better be more realistic and be much cheaper to produce so which area are you most excited for the possibility of the prices of games coming down the games looking better or the games being more realistic let me.

know what you think in the comments section below so that rounds at the end of the video my goal with all of this content on this channel is to bring something a little different to YouTube and you take on presenting information if you want to support this vision feel free to subscribe to this channel and share this video to someone wholl be interested in the topic that really helps me out if youre looking for more and want to be surprised on the variety of things that AI neural networks are capable of stick.

around and Ill leave a link to my neural network compilation video for you to have a look at its well worth for watch oh yeah and dont forget to check out my Instagram Ive been more active there recently anyway thanks for watching this has been – go go youve been watching cold fusion and Ill see you again soon for the next video cheers guys have a good one .are you thinking

Core entities

Andrew price

Pixar

Bayerische Motoren Werke AG

CGI

Georgia Tech

Core concepts

video game

neural network

real-time ray

ray tracing

procedural content generation

video games

cold fusion

playing games

stranger things

board game

style transfer

creative fields

real-time video games

real-time ray tracing

video game artists

realistic buildings cars