V clanku jsou i dalsi chyby. Mozna schvalne? Uz nekolikrat jsem tu mluvil o DLSS jako supersamplingu.
"Maudit 23.8.2018 at 2:14
Ta sama dnn se samozrejme da pouzit I ke zvyseni rozliseni (Huang to tam rika, treba vylepseni CT scanu), kdyz tu extra informaci (extra samply) nepouzijes k antialiasingu, ale primo na vykresleni dalsiho pixelu. Ale v kontextu supersample antialiasingu jsou ty extra samply pouzity k vyhlazovani (proto to tak pojmenovali LOL)."
TechPowerUp by W1zzard, on Sep 14th, 2018
"NVIDIA also speak of a DLSS 2X setting, which renders the image at the intended target resolution and then upscales it via its AI-based neural network to quality levels approaching those of a natively rendered 64x super sample rendering."
https://www.techpowerup.com/reviews/NVIDIA/GeForce_Turing_GeForce_RTX_Architecture/9.html
DLSS tak scenu vyrenderovanou ve 4k posune treba na 8k a tu informaci pouzije pro vylepseni puvodniho 4k obrazu. Proc tohle v clanku chyby? ;) Nekdo se neceho boji? :D