Skip to main content

Nvidia’s DLSS 2.0 to bring boosted frame rates without the blurry textures

 

Just last week, Nvidia and Microsoft announced new ray tracing features with the launch of DirectX 12 Ultimate. Now, Nvidia is following that up with a second iteration of its DLSS (deep learning super sampling) technology. Nvidia claims DLSS 2.0 will greatly improve game visuals and performance using its artificial intelligence-based approach to rendering.

Recommended Videos

The format was originally introduced with Nvidia’s Turing architecture, which debuted on the company’s GeForce RTX 2080 graphics. DLSS uses machine learning to analyze tens of thousands of reference images to help increase frame rates.

Unlike the olde,  temporal anti-aliasing-based rendering approach, DLSS conserves system resources by examining a lower resolution scene and compares it to the reference images to determine how the scene should be rendered at a higher resolution. For Nvidia, it was a way of compensating for the heavy toll that ray tracing took on performance.

With DLSS 2.0, Nvidia aims to close the performance gap further. Even on midrange GPUs like the RTX 2060, Nvidia claims you should see a boost in frame rates, visual fidelity, and scene details.

Nvidia DLSS 2.0 update
Nvidia showcases DLSS 2.0 on Mechwarrior 5 Nvidia

Nvidia executives showcased the power of DLSS in a number of demos prior to the feature’s announcement, comparing the performance with DLSS 2.0 enabled at 1440p resolution against a game without the feature turned on. The result was delightfully impressive.

In Mechwarrior 5, with DLSS disabled at 1440p resolution on the RTX 2060, the game played at a respectable 71 frames per second. With DLSS 1.0 enabled, performance jumped to 95 FPS, and you’re getting more visual details, better colors, and more realism — it’s like HDR for your game.

In the demo, the colors in the landscape were punchier, and the scene appears sharper, though text appears slightly blurry, a likely result of oversharpening. With DLSS 2.0 enabled, the scene benefits from the same enhanced details as DLSS 1.0, but here text appears to be crisper. Nvidia was able to achieve a similarly high 95 FPS with the new update, showing that you’re not trading off game performance for visual fidelity.

Nvidia

Control DLC will get updated to DLSS 2.0, and in that game, Nvidia showed that even peripheral background text in the game’s scene also gets sharpened, making text and details easier to read and see. When the game is played at 1080p resolution, you’re getting almost a 70 percent boost in frame rates with DLSS 2.0 enabled.

Whereas a game at 1080p played at just 36 FPS without DLSS, the same game jumps to 61 FPS with DLSS 2.0 while also providing upgraded visual fidelity, showing more details.

For fast, action-packed games, DLSS 2.0 will also improve the image quality of objects in motion, so you’re going to see crisper movements throughout the game. DLSS 2.0 is available now, Nvidia said, on titles such as Wolfenstein: Youngblood, Deliver Us the MoonMecharrior 5, and Unreal Engine, with dozens more titles coming soon.

Chuong Nguyen
Silicon Valley-based technology reporter and Giants baseball fan who splits his time between Northern California and Southern…
9 macOS Sequoia features every Mac user should know
macOS Sequoia being introduced by Apple's Craig Federighi at the Worldwide Developers Conference (WWDC) 2024.

Apple’s macOS Sequoia operating system launched with a whole heap of interesting new features, and there’s a lot to try if you’ve just recently updated your Mac. But which new additions are worth your time, and which can be passed over?

That’s the question we’re aiming to answer today. We’ve scoured macOS Sequoia to find the nine key features that every Mac user should know about. From Apple Intelligence to iPhone Mirroring, these are the tools and technologies that you’ll want to try next.

Read more
Meta is training AI on your data. Users say opting out doesn’t work.
Meta AI WhatsApp widget.

Imagine a tech giant telling you that it wants your Instagram and Facebook posts to train its AI models. And that too, without any incentive. You could, however, opt out of it, as per the company. But as you proceed with the official tools to back out and prevent AI from gobbling your social content, they simply don’t work. 

That’s what users of Facebook and Instagram are now reporting. Nate Hake, publisher and founding chief of Travel Lemming, shared that he got an email from Meta about using his social media content for AI training. However, the link to the opt-out form provided by Meta doesn’t work.

Read more
Your politeness toward ChatGPT is increasing OpenAI’s energy costs 
ChatGPT's Advanced Voice Mode on a smartphone.

Everyone’s heard the expression, “Politeness costs nothing,” but with the advent of AI chatbots, it may have to be revised.

Just recently, someone on X wondered how much OpenAI spends on electricity at its data centers to process polite terms like “please” and “thank you” when people engage with its ChatGPT chatbot.

Read more