pixpark/gpupixel

Real-time image filter engine based on GPU

What it solves

GPUPixel is designed to provide high-performance image and video filtering, specifically focusing on beauty filters, across multiple platforms. It addresses the need for a lightweight, cross-platform library that can apply visual effects to media in real-time.

How it works

Built with C++11 and OpenGL/ES, the library leverages the GPU to process image and video frames. It is compatible with any OpenGL/ES platform, allowing it to run on iOS, Android, Mac, Windows, and Linux.

Who it’s for

Developers building applications that require real-time image or video processing, such as camera apps, video editors, or social media platforms that need beauty filters.

Highlights

  • High-performance processing using OpenGL/ES.
  • Cross-platform support for iOS, Android, Mac, Windows, and Linux.
  • Small footprint for efficient integration into mobile and desktop apps.
  • Specialized beauty filters for visual enhancement.

Related

  • Project
    isl-org/Open3D-ML

    An extension of Open3D that provides tools, pretrained models, and pipelines for 3D machine learning tasks like semantic segmentation and object detection.

  • Project
    frgfm/torch-cam

    A PyTorch library for visualizing class activation maps (CAM) to explain and debug the predictions of convolutional and transformer-based vision models.

  • Project
    Smorodov/Multitarget-tracker

    A comprehensive multi-target tracking framework that combines SOTA deep learning detectors, matching algorithms, and Kalman filters to follow multiple objects in video.

  • Project
    schappim/macOCR

    A command-line OCR tool for macOS that extracts text, QR codes, and barcodes from the screen, images, or PDFs using Apple's Vision framework.