NVIDIA/DLSS

NVIDIA DLSS is a new and improved deep learning neural network that boosts frame rates and generates beautiful, sharp images for your games

What it solves

It provides a set of tools for high-performance image scaling and sharpening in games and graphics applications, allowing developers to upscale images to higher resolutions while maintaining visual quality.

How it works

The project provides a SDK that includes compute shaders that can be integrated with DirectX 11, DirectX 12, and Vulkan APIs to perform spatial scaling and sharpening.

Who it’s for

Game developers and graphics engineers who need to integrate NVIDIA's image scaling and DLSS technologies into their applications.

Highlights

  • SDK for NVIDIA RTX DLSS
  • Cross-platform support for spatial scaling and sharpening
  • Integration support for DX11, DX12, and Vulkan

Related

  • Project
    ANTsX/ANTs

    A C++ library for high-dimensional medical image registration and segmentation, used to analyze brain structure and function across species and organ systems.

  • Project
    pur1fying/blue_archive_auto_script

    An automation script for Blue Archive that uses YOLOv8 for character detection to automate combat, daily tasks, and resource management.

  • Project
    google/GNM

    A family of parametric statistical 3D human models, starting with GNM Head, for high-fidelity representation of human geometry and appearance.

  • Project
    koide3/direct_visual_lidar_calibration

    A target-less, automatic toolbox for LiDAR-camera extrinsic calibration that uses environment structure and texture for precise sensor alignment.