Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizen OC_Formula for the clue delivery! CTOnews.com Sept. 24, Nvidia answers players' questions about DLSS 3 in its latest blog post.

Nvidia says DLSS 3 includes three technologies: DLSS frame generation, DLSS super resolution (also known as DLSS 2) and NVIDIA Reflex. Among them, DLSS frame generation requires hardware support from the latest RTX 40 graphics card, which can be supported by DLSS 2 and NVIDIA Reflex cash graphics cards.

Nvidia said that the DLSS frame generation feature uses the high-speed RTX 40 Series Optical flow Accelerator to calculate the motion flow for the AI network, and then executes the network on the fourth-generation Tensor Core. To support the previous GPU architecture, it is necessary to further innovate and optimize the optical flow algorithm and AI model.

Of course, existing hardware will still support DLSS Super Resolution and NVIDIA Reflex, so current GeForce gamers and creators will benefit from integrated DLSS 3 games. Nvidia will continue to study and train AI for DLSS super resolution and will provide model updates to all RTX customers as it has done since DLSS was first released.

Q: DLSS 3.0 looks great and is impressive on a technical level. Do you need to update at the engine level to experience the improvements of DLSS 3.0 over 2.0? Or is it possible to easily implement DLSS 3.0 in games that already support DLSS 2.0 without a lot of development work?

A lighter and simpler integration approach has always been the design goal of DLSS 3. With more than 35 games and apps coming soon, DLSS 3 has become one of Nvidia's fastest-growing technologies. The first games that support DLSS 3 will be launched in October.

DLSS 3 leverages the same integration points as DLSS 2 and NVIDIA Reflex to easily upgrade existing SDK through the DLSS 3 Streamline plug-in.

DLSS 3 is also about to be used in the world's most popular game engines, including Unity, Unreal engine and Frost engine, making it easy for games based on these engines to switch to DLSS 3.

Q: how does the optical flow fit into the model? If DLSS 2 is a spatial reconstruction of the next frame, does this mean that we reconstruct the timing of the previous multiple frames? In addition, can it achieve less than 25% pixel rendering (DLSS performance mode)?

There are two AI models in DLSS 3: DLSS Super Resolution (also known as DLSS 2) and DLSS frame generation. DLSS Super Resolution increases the frame rate by rendering fewer pixels and then using AI to build a sharper image with a higher resolution. The DLSS frame generation feature generates additional high-quality frames by analyzing the continuous frames and motion data of the Optical flow Accelerator in the GeForce RTX 40 Series GPU, thereby improving performance and maintaining excellent picture quality and response speed. When DLSS 3 is enabled, the first frame is first reconstructed by DLSS super-resolution, and the subsequent frames are reconstructed by DLSS frame generation. Overall, DLSS 3 is able to reconstruct the total number of pixels displayed in 7 to 8.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.