转至内容
商品 NVIDIA DLSS 4 的媒体 1

描述

DLSS 4 neural rendering technologies include DLSS Multi Frame Generation, DLSS Frame Generation, DLSS Ray Reconstruction, DLSS Super Resolution, Deep Learning Anti-Aliasing and others.

 

  • DLSS Multi Frame Generation (MFG) boosts frame rates by using AI to generate up to three frames per rendered frame, while maintaining responsiveness with NVIDIA Reflex. Blackwell’s 5th generation Tensor Cores and display engine with improved flip metering deliver the AI horsepower and optimal frame pacing for a seamless gaming experience. 

  • DLSS Frame Generation (FG) boosts performance by using AI to generate frames while maintaining great responsiveness with NVIDIA Reflex for GeForce RTX 40 Series GPUs. 

  • DLSS Ray Reconstruction (RR) enhances image quality by using AI to generate additional pixels for intensive ray-traced scenes. DLSS replaces hand-tuned denoisers with an NVIDIA supercomputer-trained AI network that generates higher-quality pixels between sampled rays.

  • DLSS Super Resolution (SR) boosts performance by using AI to output higher-resolution frames from a lower-resolution input. DLSS samples multiple lower-resolution images and uses motion data and feedback from prior frames to construct high-quality images. 

  • Deep Learning Anti-Aliasing (DLAA) provides higher image quality with an AI-based anti-aliasing technique. DLAA uses the same Super Resolution technology developed for DLSS, constructing a more realistic, high-quality image at native resolution. 

  • RTX Dynamic Vibrance (RTXDV) enhances visual clarity by dynamically tuning color, saturation and contrast.

  • NVIDIA Image Scaling (NIS) boosts frame rates using GPU scaling and sharpening.

  • NVIDIA Reflex Low Latency reduces PC latency and increases responsiveness.

  • DLSS Movie Render Queue adds DLSS/DLAA support to Movie Render Queue.

DLSS Super Resolution, Ray Reconstruction, and DLAA now use a new transformer AI model trained by NVIDIA’s supercomputers for improved stability from one frame to the next, enhanced lighting detail, and more detail in motion.

Last updated: February 2025

标签