U F1 bylo DLSS rozbity. Proto byl videt ten temporalni charakter - kvuli chybe. U FF neznamena absence rozmazani absenci temporalniho prvnku. Znamena absenci ty chyby, ktera byla v F1. DLSS bylo a je temporalni od zacatku. Uz v prni prezentaci Huanga to bylo, v blog postech to bylo. Vsechno si oznacil za marketingovy reci.
V tom whitepaperu to taky je, hned na zacatku:
"DEEP LEARNING SUPER-SAMPLING (DLSS)
In modern games, rendered frames are not displayed directly, rather they go through a post processing image enhancement step that combines input from multiple rendered frames, trying to remove visual artifacts such as aliasing while preserving detail. For example, Temporal Anti-Aliasing (TAA), a shader-based algorithm that combines two frames using motion vectors to determine where to sample the previous frame, is one of the most common image enhancement algorithms in use today. However, this image enhancement process is fundamentally very difficult to get right.
NVIDIA’s researchers recognized that this type of problem - an image analysis and optimization problem with no clean algorithmic solution - would be a perfect application for AI."
https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf
(strana 34)
Jasne tam definujou problem - moderni algoritmy pouzivaji temporalni pristup. A ted pozor - jako problem definujou schopnost spravne kombinovat data z vic snimku. A v zapeti mluvi o tom, ze na jeho reseni je idealni pouzit AI. Nikde se tam nepise ani slovo o tom, ze DLSS je spatial technika.