‹ BackHN Continuity

Thread

OpenDLSS: A Vulkan Reimplementation of Nvidia's DLSS 5 Neural Rendering Network

277 points · 126 comments · sagacity

  1. franticgecko3 · · focus · HN ↗
    How useful is this without weights?

    Isn't the mote that Nvidia has is they work with studios to generate the training data from the game, then they ship a model per game?

    Or is my knowledge outdated here and they're just using a single generalised model?

    1. GaggiX · · focus · HN ↗
      >they ship a model per game?

      They don't. Only DLSS 1 was trained specifically per each game.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.