Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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Or is my knowledge outdated here and they're just using a single generalised model?

 help



I assume this is meant to run with the weights people extracted from the latest NBA game, where it was first trialled.

> 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?

That was true for the very first version of DLSS, from DLSS 2 on the models have been universal - the per-game adjustments are done on the inference end by changing the effect intensity or masking out objects

They have a technical report on the neural rendering part of DLSS 5 which goes into it: https://research.nvidia.com/labs/adlr/files/DLSS5_Report.pdf


>they ship a model per game?

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


They used to ship one model per game but now there is a single model, however they still do minor updates to it presumably to fine-tune it on new games

> they ship a model per game?

there's no way that's true!?


It used to be in dlss1. I think it's completely been put to pasture now though, it's way too much work and can't really cover some of the main things people actually want to use dlss5 on, for instance Morrowind.

its not, from what I've heard the difference in quality was not worth it

I don't really understand why the weights aren't included... US law says they can't have a copyright, no? Maybe they're concerned about other countries or cautious about a litigious Nvidia.

The US has a copyright law.

American copyright, as opposed to most European copyrights, only protects creative works. Fully machine generated weights are not creative as no human touched them. You can copyright the training code, you can't copyright the output.

There is an argument that it's a derivative work and it's therefore copyrighted under the same protection as the training data, but that gives the rights to the owners of the training data, not the ai-lab. Courts are seemingly mostly rejecting this though as it's different enough to be fair use.




Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: