NVIDIA DLSS (Deep Learning Super Sampling) is a suite of neural rendering technologies powered by GeForce RTX™ Tensor Cores that boosts frame rates while delivering crisp, high-quality images that rival native resolution. The latest breakthrough, DLSS 4, brings new Multi Frame Generation, and in unison with the suite of DLSS technologies, increases performance by up to 8X over traditional rendering while maintaining responsiveness with NVIDIA Reflex.

Features

• DLSS Multi Frame Generation: Uses AI to generate up to three frames per rendered frame, powered by GeForce RTX 50 Series and fifth-generation Tensor Cores.
• DLSS Frame Generation: Boosts performance by using AI to generate frames while maintaining great responsiveness with NVIDIA Reflex.
• DLSS Ray Reconstruction: Enhances image quality by using AI to generate additional pixels for intensive ray-traced scenes, replacing hand-tuned denoisers with an NVIDIA supercomputer-trained AI network.
• DLSS Super Resolution: Boosts performance by using AI to output higher-resolution frames from a lower-resolution input, sampling multiple lower-resolution images and using motion data and feedback from prior frames.
• Deep Learning Anti-Aliasing (DLAA): Provides higher image quality with an AI-based anti-aliasing technique, constructing a more realistic, high-quality image at native resolution.

Benefits

• Performance Multiplier: DLSS 4, featuring DLSS Multi Frame Generation, multiplies frame rates by up to 8X over traditional brute-force rendering.
• Maximize Quality with AI: Takes advantage of AI models continuously improved through ongoing training on NVIDIA supercomputers, providing better image quality and performance across more games and applications.
• Enhanced Ray Tracing: Replaces the need for multiple hand-tuned denoisers and generates higher-quality pixels between sampled rays.
• Seamless Integration: Easily integrates with game engines like Unreal Engine and Unity, providing access to DLSS technologies through plugins.