Skip to content

sakamoto111111/retinify

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

329 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

logo

Real-Time AI Stereo Vision Library

UBUNTU 24.04 UBUNTU 22.04 Release License Language
X LinkedIn YouTube

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.

Why Retinify?

  • 🌐 Open Source: Fully customizable and freely available under an Apache-2.0 license.
  • πŸ”₯ High Precision: Delivers real-time, accurate 3D mapping and object recognition from stereo image input.
  • ⚑ Fast Pipeline: All necessary computations run seamlessly on the GPU, enabling real-time performance.
  • πŸŽ₯ Camera-Agnostic: Accepts stereo images from any rectified camera setup, giving you the flexibility to use your own hardware.
  • πŸ’° Cost Efficiency: Runs using just cameras, enabling depth perception with minimal hardware cost.

Basic Usage

pipeline

Important

Retinify is independent of OpenCV and supports various image data types.

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

// LOAD INPUT IMAGES
cv::Mat leftImage = cv::imread("path/to/left.png");
cv::Mat rightImage = cv::imread("path/to/right.png");

// PREPARE OUTPUT CONTAINER
cv::Mat disparity = cv::Mat::zeros(leftImage.size(), CV_32FC1);

// CREATE STEREO MATCHING PIPELINE
retinify::Pipeline pipeline;

// INITIALIZE THE PIPELINE
pipeline.Initialize(leftImage.cols, leftImage.rows);

// EXECUTE STEREO MATCHING
pipeline.Run(leftImage.ptr<uint8_t>(), leftImage.step[0],   //
             rightImage.ptr<uint8_t>(), rightImage.step[0], //
             disparity.ptr<float>(), disparity.step[0]);

Getting Started

πŸ“– retinify documentation β€” Developer guide and API reference.

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

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

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

Supported Backends

🎯 Target Status
target_tensorrt_badge build_tensorrt_badge
target_jetson_badge build_jetson_badge
target_hailort_badge Coming soon
target_openvino_badge Coming soon

Pipeline Latencies

Latency includes the time for image upload, inference, and disparity download, reported as the median over 10,000 iterations (measured with retinify::Pipeline).
These measurements were taken using each setting ofβ€―retinify::Mode.

Note

Results may vary depending on the execution environment.

DEVICE \ MODE FAST BALANCED ACCURATE
NVIDIA RTX 3060 3.925ms / 254.8FPS 4.691ms / 213.2FPS 10.790ms / 92.7FPS
NVIDIA Jetson Orin Nano 17.462ms / 57.3FPS 19.751ms / 50.6FPS 46.104ms / 21.7FPS

Third-Party

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

Contact

For commercial inquiries, additional technical support, or any other questions, please feel free to contact us at contact@retinify.ai.

About

Real-Time AI Stereo Vision Library

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • C++ 84.9%
  • CMake 9.6%
  • Cuda 4.0%
  • Shell 1.5%