Retinify is an advanced AI-powered stereo vision library designed for robotics. It enables real-time, high-precision 3D perception by leveraging GPU and NPU acceleration.
Its C++ API allows the same code to run seamlessly across various acceleration backends.

• 🌐 Open Source: Fully customizable and freely available under an open-source license.
• 🔥 High Precision: Delivers real-time, accurate 3D mapping and object recognition from stereo image input.
• 💰 Cost Efficiency: Runs using just cameras, enabling depth perception with minimal hardware cost.
• 🎥 Camera-Agnostic: Accepts stereo images from any rectified camera setup, giving you the flexibility to use your own hardware.

retinify::tools offers OpenCV-compatible utility functions for image and disparity processing.

#include <retinify/retinify.hpp>
#include <opencv2/opencv.hpp>

// LOAD INPUT IMAGES
cv::Mat leftImage = cv::imread(<left_image_path>);
cv::Mat rightImage = cv::imread(<right_image_path>);

// PREPARE OUTPUT CONTAINER
cv::Mat disparity;

// CREATE STEREO MATCHING PIPELINE
retinify::tools::StereoMatchingPipeline pipeline;

// INITIALIZE THE PIPELINE
pipeline.Initialize();

// EXECUTE STEREO MATCHING
pipeline.Run(leftImage, rightImage, disparity);

📖 retinify-documentation — Developer guide and API reference.

• 🚀 Installation Guide
  Step-by-step guide to build and install retinify.

• 🔨 Tutorials
  Hands-on examples to get you started with real-world use cases.

• 🧩 API Reference
  Detailed class and function-level documentation for developers.

⚡ Target	Status
	Coming soon
	Coming soon

Latency includes the time for image upload, inference, and disparity download, reported as the median over 10000 iterations.
These measurements were taken using each setting of retinify::tools::Mode.

For a list of third-party dependencies, please refer to NOTICE.md.

For any inquiries, please feel free to contact us at [email protected].
We would be pleased to assist you and look forward to hearing from you.