Displaying 1 to 20 from 329 results

Accord.NET - Machine learning, Computer vision, Statistics and general scientific computing for .NET

  •    CSharp

The Accord.NET project provides machine learning, statistics, artificial intelligence, computer vision and image processing methods to .NET. It can be used on Microsoft Windows, Xamarin, Unity3D, Windows Store applications, Linux or mobile.

vision - Datasets, Transforms and Models specific to Computer Vision

  •    Jupyter

The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us.

StarGAN - Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

  •    Python

PyTorch implementation of StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. StarGAN can flexibly translate an input image to any desired target domain using only a single generator and a discriminator.

FaceTracker - Real time deformable face tracking in C++ with OpenCV 3.

  •    C++

FaceTracker is a library for deformable face tracking written in C++ using OpenCV 2, authored by Jason Saragih and maintained by Kyle McDonald. It is available free for non-commercial use, and may be redistributed under these conditions. Please see license.md for complete details. For commercial use, request a quote.

opencv - Open Source Computer Vision Library

  •    C++

Please read the contribution guidelines before starting work on a pull request.

openFrameworks - openFrameworks is a community-developed cross platform toolkit for creative coding in C++

  •    C++

docs has some documentation around OF usage, per platform things to consider, etc. You should definitely take a look in there; for example, if you are on OSX, read the osx.md. apps and examples are where projects go -- examples contains a variety of projects that show you how to use OF, and apps is where your own projects will go. libs contains the libraries that OF uses, including the openframeworks core itself. addons are for additional functionality that's not part of the core. export is for DLLs and dylibs that need to be put in each compiled project. The scripts folder has the templates and small scripts for automating OF per platform. project generator is a GUI based tool for making new projects - this folder is only there in packaged releases. One idea that's important is that OF releases are designed to be self-contained. You can put them anywhere on your hard drive, but it's not possible to mix different releases of OF together, so please keep each release (0.8.0, 0.8.1) separate. Projects may generally work from release to release, but this is not guaranteed. Because OF is self-contained, there's extensive use of local file paths (ie, ../../../) throughout OF. It's important to be aware of how directories are structured. A common error is to take a project and move it so that it's a level below or above where it used to be compared to the root of OF. This means that links such as ../../../libs will break.

facenet - Face recognition using Tensorflow

  •    Python

This is a TensorFlow implementation of the face recognizer described in the paper "FaceNet: A Unified Embedding for Face Recognition and Clustering". The project also uses ideas from the paper "Deep Face Recognition" from the Visual Geometry Group at Oxford. The code is tested using Tensorflow r1.7 under Ubuntu 14.04 with Python 2.7 and Python 3.5. The test cases can be found here and the results can be found here.

clmtrackr - Javascript library for precise tracking of facial features via Constrained Local Models

  •    Javascript

The library provides some generic face models that were trained on the MUCT database and some additional self-annotated images. Check out clmtools for building your own models. For tracking in video, it is recommended to use a browser with WebGL support, though the library should work on any modern browser.

headtrackr - Javascript library for headtracking via webcam and WebRTC/getUserMedia

  •    Javascript

headtrackr is a javascript library for real-time face tracking and head tracking, tracking the position of a users head in relation to the computer screen, via a web camera and the webRTC/getUserMedia standard. For a demonstration see this video or try out some of the examples with a laptop that has a camera and a browser that has camera webRTC/getUserMedia support. For an overview of browsers supporting the getUserMedia standard see http://caniuse.com/stream.

pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs

  •    Python

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation. It can be used for turning semantic label maps into photo-realistic images or synthesizing portraits from face label maps. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs Ting-Chun Wang1, Ming-Yu Liu1, Jun-Yan Zhu2, Andrew Tao1, Jan Kautz1, Bryan Catanzaro1 1NVIDIA Corporation, 2UC Berkeley In arxiv, 2017.

luminoth - Deep Learning toolkit for Computer Vision

  •    Python

Luminoth is an open source toolkit for computer vision. Currently, we support object detection, but we are aiming for much more. It is built in Python, using TensorFlow and Sonnet. Read the full documentation here.

javacv - Java interface to OpenCV, FFmpeg, and more

  •    Java

JavaCV uses wrappers from the JavaCPP Presets of commonly used libraries by researchers in the field of computer vision (OpenCV, FFmpeg, libdc1394, PGR FlyCapture, OpenKinect, librealsense, CL PS3 Eye Driver, videoInput, ARToolKitPlus, and flandmark), and provides utility classes to make their functionality easier to use on the Java platform, including Android.

eos - A lightweight 3D Morphable Face Model fitting library in modern C++11/14

  •    C++

eos is a lightweight 3D Morphable Face Model fitting library that provides basic functionality to use face models, as well as camera and shape fitting functionality. It's written in modern C++11/14. An experimental model viewer to visualise 3D Morphable Models and blendshapes is available here.


  •    CSS

This github blog theme is forked from zJiaJun. I use this repo to organise interesting papers, projects, websites, blogs and my reading/study notes.

bgslibrary - A background subtraction library

  •    C++

The BGSLibrary was developed early 2012 by Andrews Sobral to provide an easy-to-use C++ framework for foreground-background separation in videos based on OpenCV. The bgslibrary is compatible with OpenCV 2.x and 3.x, and compiles under Windows, Linux, and Mac OS X. Currently the library contains 43 algorithms. The source code is available under GNU GPLv3 license, the library is available free of charge to all users, academic and commercial.

AlphaPose - Multi-Person Pose Estimation System

  •    Jupyter

Alpha Pose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (72.3 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset. To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset. Note: Please read PoseFlow/README.md for details.

openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, and hands estimation

  •    C++

OpenPose represents the first real-time multi-person system to jointly detect human body, hand, and facial keypoints (in total 135 keypoints) on single images. For further details, check all released features and release notes.

pix2pix - Image-to-image translation with conditional adversarial nets

  •    Lua

Image-to-Image Translation with Conditional Adversarial Networks Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros CVPR, 2017. On some tasks, decent results can be obtained fairly quickly and on small datasets. For example, to learn to generate facades (example shown above), we trained on just 400 images for about 2 hours (on a single Pascal Titan X GPU). However, for harder problems it may be important to train on far larger datasets, and for many hours or even days.