NVIDIA AI Takes Gaming to New Heights with DLSS 3.5 and Ray Reconstruction

If you’re an avid gamer, you’ll have already heard of ray tracing and NVIDIA. DLSS (Deep Learning Super Sampling), two powerful tools that combine to improve game performance and deliver stunning visual fidelity by reproducing realistic lighting and reflections. NVIDIA pioneered these technologies in gaming with the introduction of its RTX 20 series graphics cards, and over the two hardware generations that followed, the AI ​​techniques and hardware behind them have evolved. are considerably improved. With DLSS 3.5 and a new ray reconstruction system working hand in hand, ray tracing games can look all the more realistic and run much smoother at the same time. So how do these technologies work?

DLSS is an evolving technology. In its early days, the focus was on rendering games at a lower resolution and easier to process, then increasing the output resolution by filling in the gaps between pixels, giving gamers the benefit of sharper visuals with increased frame rates at lower resolution. NVIDIA achieved this by training its AI model on high-quality gaming visuals so that it could understand what they should look like and know how to fill in the gaps when stretching a game‘s lower resolution images to higher resolution images. higher resolutions. This process could also be reversed somewhat with DLAA (Deep Learning Anti-aliasing), which can render at a screen’s native resolution but use the same AI logic to determine what an even higher resolution image would look like , then downsample it to produce an effectively anti-aliased image.

With DLSS 3, it introduced Frame Generation, which fills pixel data between frames. While DLSS has always relied on the special Tensor cores inside RTX GPUs, which handle AI operations, DLSS 3 Frame Generation leverages even more hardware in RTX 40 series GPUs, like stream accelerators optics, to understand how objects in games move and intelligently. mix images for even smoother visuals. The combination of super sampling and Frame Generation technology in DLSS can significantly increase frame rates in games without compromising visual quality.

Alongside these developments in DLSS, NVIDIA has continued to advance its RTX ray tracing technology. Ray tracing remains a computationally intensive process, especially to obtain the most realistic results. This requires simulating a staggering amount of light rays and all their reflections between a light source and the viewer, making it unreasonable to perform this for every pixel of every frame of a fast-paced game. But taking a reasonable number of light ray samples produced a noisy image and required specially trained denoisers to obtain a usable image. Even then, the results could lack detail or exhibit unusual ghosting artifacts, and the denoisers needed to handle many ray tracing effects could still slow performance.

NVIDIA DLSS 3.5 introduced Ray Reconstruction to solve this problem. With Ray Reconstruction, all denoisers (and their corresponding computing needs) are replaced. Just as DLSS and Frame Generation use AI to understand how to intelligently fill pixels, Ray Reconstruction uses AI to fill in the gaps between simulated light rays. Ray Reconstruction has a deeper understanding of the games it runs on and their ray tracing effects, allowing it to know when to use different techniques to fill in missing data, helping it deliver crisp visuals without artifacts.

For gamers, higher resolutions and higher graphics settings once meant big framerate sacrifices. But technologies built into DLSS 3.5, like Frame Generation and Ray Reconstruction, flip the script.

Now gamers using any RTX GPU can experience realistic worlds with ray-traced lighting, shadows, and reflections while enjoying higher resolutions. And those gaming on RTX 40-series GPUs can leverage frame generation for a further boost in frame rate. Taking advantage of these technologies is as simple as running an NVIDIA RTX GPU on your desktop or laptop (or even leveraging one through NVIDIA’s GeForce NOW Ultimate or Priority service) and making sure to enable these features in your games. You can find all games and apps that support NVIDIA DLSS technologies here.

The way NVIDIA has leveraged AI to improve the gaming experience is just one of the ways the company is putting AI to work. With NVIDIA’s RTX hardware, you can do much more than game, and NVIDIA AI Decoded Blog series highlights many ways you can take advantage of your RTX hardware by running all kinds of AI-based tools.