Posted by Megalith 11:51 AM (CDT)
Sunday July 17, 2016
In a recent interview, Tim Sweeney mentioned that photo-realistic scenes are probably do-able with 40 TFLOPS of computing power. However, rendering realistic humans requires something else entirely, as there is no algorithm that can replicate all the nuances of how someone may move and act in a given situation.
Humans are the harder part, but that’s justآ…We know exactly how real world physics of lighting work, and so that’s just a matter of brute force computing power. Give us enough computing power, and we can do that. We could do that today with algorithms that we know. Humans are a much harder problem, because rendering faces and skin is hard enough, but you quickly realize that the challenge with rendering humans is having realistic human motion to display. Having dynamic human responses in games are reactive to what you’re doing, and aren’t just pre-baked.