YHK - yet another hacker news clone

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

36 points sagacity 1 day ago 24 comments

Borealid 42 minutes ago | parent

Am I the only one who feels a sense of disinterest in a project where the main README is LLM-generated? Does the author not have time to write what they did and how it's used?

fwlr 32 minutes ago | parent

If you think about it, actually the author did write what they did (nothing), and also how it’s used (it isn’t).

gnud 26 minutes ago | parent

Seems like the owner of the github repo claims copyright, though. Since they provide a license.

ChrisRR 29 minutes ago | parent

I'm fine with it

MadameMinty 25 minutes ago | parent

I'm more upset about it being factually wrong, e.g. both mentions of "git-ignored" are absurd (why would you mention it if it's not in the repo?) and wrong (they are in the repo).

vincnetas 17 minutes ago | parent

I notice this, that AI likes to write about things that are not in there. Like i review AI generated output, notice unnecessary things, and asks AI to remove that. So AI removes that and adds that "this and that that was used or described like this was removed because bla bla bla" to the document.

I think its somehow needs to talk (write) about the things that are in the context and removal is there so AI predicts that it should be there.

MadameMinty 10 minutes ago | parent

Yeah, I call it bugfix storytelling. Once upon a time this class far far away had this red hooded method...

Especially egregious if both adding and removing the thing happens in one commit. Git should be telling the story, and if it can't then there _is_ no story!

stuaxo 1 minute ago | parent

AI writing is just bad, this things is really noticable - but even in READMEs they look superficially OK until you read them.

AI probably should not be writing docs, commit logs or comments.

rvz 8 minutes ago | parent

If the README is >90% AI generated and it is as long as a novel, I am not going to read it and will assume that the author did not read or write it either.

Unfortunately it is slop, beyond the comprehension of the author unless they are experienced with DLSS internals to explain it in depth.

tim-projects 30 minutes ago | parent

Jensen : Nobody needs to code anymore...

Programmer: OpenDLSS...

Jensen : Wait. Not like that! (╯°□°）╯︵┻━┻

rvz 20 minutes ago | parent

But I thought Nvidia “loves open source” (they don’t) and they are now a supporter for open source and open weight models by acquiring Huggingface? (They don’t actually care)

But the line is drawn when it involves CUDA and any part of their closed source compilers (nvcc).

There are obvious reasons why they are closed source, but it’s becoming pointless since Deepseek have open sourced their AI compiler and compute libraries with DeepGEMM and eventually they will catch up.

lucrbvi 3 minutes ago | parent

They only care because open-weight helps to drive the GPU business notably thanks to inference providers (Baseten, Together, Mistral, ...).

At least their support helps the open-weight ecosystem.

franticgecko3 18 minutes ago | parent

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?

chii 11 minutes ago | parent

> they ship a model per game?

there's no way that's true!?

GaggiX 8 minutes ago | parent

>they ship a model per game?

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

Pifpafpouf 6 minutes ago | parent

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

strangecasts 2 minutes ago | parent

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

flohofwoe 17 minutes ago | parent

Almost 8ms on 1080p resolution seems extremely expensive, does the original also eat into the rendering budget as much?

robinduckett 9 minutes ago | parent

The original does tend to reduce the FPS by half or more

MYEUHD 3 minutes ago | parent

Yes the original is very expensive. It depends on the resolution and the GPU used:

RTX 5060: 9.9 ms at 1080p

RTX 5070: 10.2 ms at 1440p

RTX 5080: 13.7 ms at 2160p

RTX 5090: 8.2 ms at 2160p

Source: https://www.youtube.com/watch?v=3EfLjmdG29Q&t=600

LaurensBER 2 minutes ago | parent

The current implementation is more of a tech demo than a practical way to play games (+ officially it's available in 1 game). It's _fast enough_ to make some impressive YouTube videos but you most likely won't want to play anything with it yet.

Nvidia has stated that they're still working on improving the performance. No doubt future hardware generations will also include further hardware optimisations.

The potential for this kind of technology is pretty awesome, especially given that people have also found ways to add this to emulators.

TheJCDenton 5 minutes ago | parent

> bit-exact against the original

What kind of sorcery is this ? Very impressive work !

Lerc 5 minutes ago | parent

I'm rather surprised that it doesn't take the z-buffer as an input. I would have thought that would have provided useful information, it's one of the more useful forms of contolnet.

avaer 1 minute ago | parent

Even relatively small RGB -> depth models are pretty good. Which kind of implies adding depth would not really reduce entropy, while costing bandwidth.