#237 · Primary category: Computer Vision
GPUImage2
GPUImage 2 is a BSD-licensed Swift framework for GPU-accelerated video and image processing.
Project last updated:02/16/24
GitHub Stars
4.9K
Forks
618
Contributors
20
License
BSD-3-Clause
Why we included this project
GPUImage2 gives Swift developers a straightforward way to run realtime image and video processing on the GPU instead of the CPU, with a pipeline model that links a camera, movie, or still image through a chain of filters to a view, file, or raw data. It bundles a large set of ready-made operations, including color adjustments, blurs, and edge detection such as Sobel, so common effects become a few lines of Swift rather than a graphics programming project. The framework runs on Mac, iOS, and Linux, and it is light enough to handle live 720p edge detection on a Raspberry Pi, which makes it a sensible choice for embedded or machine-vision experiments where realtime throughput matters. Developers who used the original Objective-C GPUImage will recognize the architecture, and newcomers can pick up the operator-based chaining syntax quickly.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)