NVIDIA DLSS

NVIDIA - 2月 11, 2021

NVIDIA DLSS is a deep learning neural network that uses the power of the NVIDIA RTX Tensor Cores to boost frame rates and generate sharp frames that approach or exceed native rendering.

  • サポートされたプラットフォーム
  • サポートされたエンジンバージョン
    4.26

NVIDIA DLSS (Deep Learning Super Sampling) is groundbreaking AI rendering technology that takes visual fidelity to a whole new level using dedicated Tensor Core AI processors on GeForce RTX™ GPUs. DLSS taps into the power of a deep learning neural network to boost frame rates and generate beautiful, sharp images for your games. Game devs now get performance headroom to maximize ray tracing settings and increase output resolution.

 

Features:

  • Uncompromised Quality with Higher Performance: Enjoy ray tracing and ultra-high resolutions with NVIDIA DLSS technology. It uses advanced AI rendering to produce image quality that’s comparable to native resolution--and sometimes even better--while only conventionally rendering a fraction of the pixels. New temporal feedback techniques give you incredibly sharp image details and improved stability from frame to frame.
  • Customizable Options: DLSS lets you choose several image quality modes—from Quality to Ultra Performance. You can choose how you want to balance quality and performance by controlling the game’s internal rendering resolution. Performance mode enables up to 4X AI super resolution (i.e. 1080p -> 4K) while the new Ultra-Performance mode enables up to 9X AI super resolution (1440p -> 8K)

テクニカルノート

Fully integrated into the Unreal Editor UI

Includes Blueprint library for seamless integration of DLSS into application logic

Support for packaged projects as well as for Editor focused workflows

Supported Development Platforms: Windows 64-bit

Supported Target Build Platforms: Windows 64-bit

Supported RHIs: VulkanRHI, D3D11RHI, D3D12RHI

Minimum Driver Requirement: 461.40 Grab the latest driver from nvidia.com.

Documentation: DLSS Plugin Installation Guide

Example Project: NGXTest Sample Project on GitHub