Počelo je s ovim ...
Citiraj:
|
DLSS takes advantage of AI models that are continuously improved through ongoing training on nVidia supercomputer that’s been specifically trained to analyse that image in ultra-high fidelity 16K, compare that to low resolution, and create a model to interpolate the differences. Tensor Core is accessing the AI model compiled by the supercomputer and then written into an nVidia game-ready driver. That model allows the GPU to output crisp, high resolution images much faster than traditional rendering. Rendering an image at 4K natively takes a lot of grunt, but using DLSS to deliver an image close to the same fidelity of native 4K takes just 25-50% of the computational power – the upshot of this is significant performance gains.
|
... i ajde vredu rekli su ljudi, pošto nikad jači hardver nije u stanju nativno vrtjeti najnovije naslove, nek se 1080p pomoću upscaling tehnike vrti u 4K rezoluciji, a marketing to onda prezentira kao ubrzanje. Iz generacije u generaciju došlo je do toga da se i najnovije kartice sad po defaultu moraju oslanjati na sve moguće trikove, tako da npr. 1080p@60Hz kroz DLSS upscaling i multi-frame AI generatore ispada kao 4K@240Hz
+ neki random FPS broj u gornjem desnom kutu ekrana, a cijeli doživljaj za krajneg korisnika je i dalje na nivou 1080p@60Hz izleta.