DF Direct Special: PlayStation QSSR - AI Upscaling For Standard PS5 - A Current-Gen Gamechanger?
Digital Foundry Direct Weekly
October 3, 2026
A surprise to be sure - and a welcome one. Out of the blue, Sony has released QSSR - Quick Spectral Super Resolution - a refactoring of PS5 Pro's PSSR for the standard PlayStation 5. In this video, Rich and Oliver share their initial thoughts on the technology.
Speakers Richard Leadbetter, Oliver Mackenzie
Richard Leadbetter (0:02)
It's not often we're genuinely surprised and impressed by an unheralded, completely out of the blue, new technological release. But here we are today with Sony's QSSR, available now, patched into Marvel's Wolverine and Ghost of Yote. And although we have only two games to look at, the results are very, very promising. So put simply, you could think of QSSR, a quick spectral super resolution as a companion technology to PS5 Pro's PSSR, PlayStation's spectral super resolution. It's been adapted for use on the standard PlayStation 5 And yes, it is a machine learning based upscaling algorithm, working on a console that, unlike the Pro, doesn't have access to 300 tops of accelerated machine learning performance. In fact, to the best of our knowledge, standard PS5 has no dedicated ML silicon at all. But I think the results here should speak for themselves.
So recently we had access to Wolverine and Yote, running on PS5 dev kits at Sony HQ. About 67 hours of unfettered access, but we're going to be mostly focusing on Wolverine today, owing to time constraints. So there's a lot to go through here.
Potentially a game changer for PlayStation 5 But joining me to go through everything, Oliver Mackenzie. Hello.
Oliver Mackenzie (1:18)
Yes, Rich. Here with some very exciting new tech that I really didn't expect to see at all on the base PlayStation 5
Richard Leadbetter (1:28)
Yeah, absolutely. Interesting stuff. So much to go through here. I guess we should kick off by talking about what is QSSR. And it's really interesting, right? Because fundamentally, the PlayStation 5 Pro has got dedicated machine learning instructions into support, which the base PlayStation 5 doesn't have. So instead, what QSSR is, is effectively a version, a refactoring of PSSR streamlined for FP16, which PS5 does support with the benefit of rapid packed math.
So we actually had the opportunity to pose some questions to Sony's Daniel Craig, not that one, Principal Engineer, Graphics R&D, SIE. So basically, he describes it as a drop in replacement for titles that already support PSSR. So effectively, there's potentially some very good news here, because when a developer is introducing PSSR support for their game, and there's a lot of the titles support that now, QSSR is effectively supported just with this drop in replacement. However, there may need to be a few days of integration, adjusting things like higher quality mipmaps, that sort of thing. So basically, yeah, it's a streamlined version of PSSR. And obviously, there are going to be changes to the quality level. I mean, fundamentally, it's got far less horsepower to work with. And at the same time, Sony is looking to produce an upscaler that has a similar cost to existing upscalers like an FSR, for example. We'll talk about performance later.
Yeah, but I guess fundamentally, there are going to be trade-offs here because there is no machine learning-based acceleration on the base PlayStation 5 But we'll talk about performance later. Anything to add to that, Oliver?
Oliver Mackenzie (3:34)
Not too much. Just to say that the general approach of basically porting over PSR from Int8 to FP16 is surprising, but that does seem like obviously that's the way that you have to go here. FP16 is a much more general and more precise data format. Int8 and FP8 tend to be very fast data formats to use on graphics hardware that can accelerate those data formats.
FP16 is used for machine learning work all the time, but it is a bit of a slower data format that might not lend itself as well, or definitely wouldn't lend itself as well, to a really advanced upscaler like the underlying neural network that's behind FSR4 and PSSR. Then I think as we can see, the results are very shippable and very intriguing, and it's not just like a proof of concept, here's something, we're throwing it out there, you can try it, whatever, this is actually something that seems pretty ready for primetime in terms of the upscaling quality.
Richard Leadbetter (4:37)
Absolutely, yeah, and I think it's really important just to put this into context, because throughout this console generation, developers have been pushing visual fidelity very, very hard, so to speak, and they also want 60 frames per second, and the impact of that has been very low resolutions, and the upscalers available, FSR being a case in point, the quality isn't particularly fantastic. So if this is like effectively a drop in replacement, that replaces FSR and other upscalers producing higher quality, and if there is a sort of equivalent computational cost to it, then the implications for this are just remarkable. It could be a game changer. And the main game that we're going to be looking at today, Marvel's Wolverine, is a pretty good example of that.
24 more minutes of transcript below
Thousands of transcripts fetched by people building searchable podcast archives
Fetch the whole transcript
The demo key returns a sample episode in full, no card needed:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000792970557