Skip to main content

Is Nvidia DLSS about to become obsolete? Here’s the proof

Nvidia Deep Learning Super Sampling (DLSS) has been the upscaling tech for over two years, but a new challenger is approaching. Ghostwire Tokyo showcases a relatively new technique in Unreal Engine 5 called Temporal Super Resolution (TSR) that looks and performs nearly as well as DLSS does, and it has a big advantage: It works with any graphics card.

DLSS has enjoyed the limelight as a proprietary supersampling technique that delivers much better image quality than competitors like AMD FidelityFX Super Resolution (FSR). Companies like AMD haven’t been idle, though, and general-purpose upscaling solutions like FSR 2.0 and TSR will make DLSS obsolete.

A spirit with a dog paw attacks in Ghostwire: Tokyo.

TSR is a feature of Unreal Engine 5, but developer Tango Gameworks was able to get it working in the UE4-based Ghostwire TokyoUnlike DLSS, it doesn’t require dedicated A.I. accelerators to work. Instead, it feeds temporal (timed-based) data into a supersampling algorithm to upscale the image.

Although TSR is an emerging feature, it’s already being put to use in other places. AMD’s upcoming FSR 2.0 overhaul is a prime example, utilizing temporal inputs that feed a supersampling algorithm. Ghostwire Tokyo provides a glimpse at the future of PC graphics: One where every game has high-quality upscaling that works across GPUs.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

The image below shows TSR, FSR 1.0, and DLSS next to each other, in that order. DLSS and TSR look identical. Even massively zoomed in, I can’t find any significant differences. Compare that to FSR 1.0, which has black spots in the blue Tottoko Cine sign, as well as a dirty edge around the green sign below it.

An upscaling comparison in Ghostwire Tokyo.
Image used with permission by copyright holder

In a scene with sharp detail, the same holds true. TSR and DLSS look the same, and FSR 1.0 has problems. Notice the TV hanging up on the left, which is much blurrier with FSR 1.0, as well as the dimmer lights going down the hallway. With FSR 1.0, these lights flickered as the upscaling algorithm struggled to keep up. With TSR and DLSS, they were stable.

A comparison of FSR, TSR, and DLSS in Ghostwire Tokyo.
Image used with permission by copyright holder

The main draw of DLSS has been its excellent image quality, which Nvidia has attributed to the dedicated Tensor cores in RTX 30-series and 20-series graphics cardsGhostwire Tokyo shows that dedicated hardware isn’t doing much. TSR looks just as good, and if FSR 2.0 is indeed similar, it should, too.

We can’t ignore performance, though. At 4K with ray tracing turned on and all of the sliders maxed out (minus motion blur), I was averaging 40 frames per second (fps). TSR was able to more than double my frame rate, boosting it to 84 fps.

It’s a massive improvement, though not quite as large as the ones offered by FSR 1.0 and DLSS. FSR 1.0 shook out with an average 90 fps, while DLSS sat on top with a 100 fps average. While 16% better performance for DLSS is significant, when TSR can already double your frame rate, it doesn’t seem as important.

We might be seeing a repeat of Nvidia G-Sync here. DLSS has been a walled garden since it launched, and TSR shows that restrictive approach may not have been necessary. As other companies push their collective knowledge to build better products for gamers, we’re getting similar image quality and performance without the need to shell out for a GPU with a certain brand on it.

FSR 2.0 and TSR are enough to kill DLSS on their own, and with Intel’s upcoming XeSS technology in the mix, the future doesn’t look bright for Nvidia’s upscaling tech. Consider game developers, too. If a solution like TSR can offer similar performance and image quality as DLSS, and it works across GPUs and consoles, that just makes more sense.

The future may not be bright for DLSS, but it is for PC gamers. If Ghostwire Tokyo is a sign of what’s to come, PC gamers are in for more upscaling options that work with more hardware while still providing near-native image quality.

Jacob Roach
Lead Reporter, PC Hardware
Jacob Roach is the lead reporter for PC hardware at Digital Trends. In addition to covering the latest PC components, from…
23% of PC gamers probably can’t play Alan Wake 2. Here’s why
Alan looks surprised in Alan Wake 2.

We've known for months that Alan Wake 2 will be one of the most demanding games on PC, but new details show just how taxing the upcoming title from developer Remedy will actually be. According to a now-deleted tweet from a Remedy employee, somewhere around 23% of PC players won't be able to play the game.

To be clear, the employee didn't say that number explicitly. In response to the outcry over the Alan Wake 2 system requirements, the employee shared that only cards with mesh shaders are officially supported, meaning any Nvidia 10-series or AMD RX 5000-series GPUs or older aren't officially supported.

Read more
I can’t get excited about AMD’s next version of FSR anymore
Hero art for Forspoken

AMD's FidelityFX Super Resolution 3 is available after nearly a year of waiting. The company announced the feature around November of last year, in a swift response to Nvidia's, at the time, new Deep Learning Super Sampling 3 (DLSS 3). AMD's pitch was simple. The company was going to deliver the same performance-multiplying feature that generates frames instead of rendering them, and it would work with any graphics card.

Now it's here, and on paper, FSR 3 does exactly what AMD claimed. It's clear AMD has a lot more work to do to make FSR 3 work properly, though. And after almost a year of waiting for the feature to arrive, it's hard betting on promises for what FSR 3 could be in the future.
Where are the games?

Read more
Nvidia is cheating with its GPUs, and that’s great for laptops
A game playing on the Razer Blade 14 gaming laptop.

With some AI trickery, Nvidia has managed to cheat the traditional rendering pipeline for games. And that makes traditionally underpowered laptops so much better.

Its latest RTX 40-series mobile GPUs are very powerful -- especially if you jump up to the RTX 4090 in a machine like the Asus Strix Scar 17. But it’s the low-end options where Nvidia is really pushing ahead. That isn’t due to raw power, but instead Deep Learning Super Sampling (DLSS), Nvidia's AI-powered upscaling and frame generation tech.

Read more