news 
Nvidia announces DLSS 4 with Multi Frame Generation
Nvidia has announced a significant upgrade to its Deep Learning Super Sampling (DLSS) technology, dubbed DLSS 4. This new iteration includes neural rendering capabilities that enable Multi Frame Generation on systems equipped with the latest RTX 50 Series GPUs.
According to Nvidia, this revolutionary technology can generate “up to three additional frames per traditionally rendered frame,” which, when combined with the existing suite of DLSS technologies, can multiply frame rates by up to 8X over traditional brute-force rendering. This means that gamers will be able to enjoy 4K 240fps, fully ray-traced gaming, a feat previously unimaginable.
The company is also introducing new transformer AI models on all GeForce RTX GPUs, allowing DLSS games with Ray Reconstruction, Super Resolution, and DLAA to be updated with the same technology used in AI tools like ChatGPT. This represents a significant step forward for the industry.
Nvidia claims that its new frame generation model boasts a 40 percent speed increase and a 30 percent reduction in VRAM usage compared to the previous version. No specific details on which features will be available on which RTX GPU series have been shared at this time, but Nvidia has provided a slide outlining the compatibility of DLSS 4 with various GPU models.
The announcement marks a major milestone for the company, as it surpasses the capabilities of its previous iterations, including DLSS 3 with Frame Generation and DLSS 3.5, which was introduced in August 2023 with an AI-powered Ray Reconstruction technique to improve ray tracing and introduce path tracing in select titles.
Source: http://www.theverge.com
