Open-source computer-vision software
1575 open-source libraries, tools and applications tagged computer-vision, ranked by how closely computer-vision is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
1575 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| open-mmlab/mmflow MMFlow is an open-source optical flow toolbox and benchmark built on PyTorch as part of the OpenMMLab project. It provides a unified, modul… | 23 | 1061 | maintenance |
| zhaoweicai/cascade-rcnn A C++/Caffe implementation of Cascade R-CNN and other popular two-stage object detection frameworks such as Faster R-CNN, R-FCN, and FPN. I… | 32 | 1059 | maintenance |
| Julioacarrettoni/UIImageView_FaceAwareFill An Objective-C category on UIImageView that applies Aspect Fill content mode while detecting faces via Core Image and centering the crop on… | 31 | 1059 | maintenance |
| zdzhaoyong/GSLAM GSLAM is a general Simultaneous Localization and Mapping (SLAM) framework and benchmark written in C++. It provides a unified plugin-based … | 23 | 1059 | maintenance |
| damo-cv/TransReID Official PyTorch implementation of TransReID, an ICCV 2021 paper applying vision transformers to object re-identification. It provides trai… | 32 | 1056 | maintenance |
| keras-team/keras-cv KerasCV is a library of modular computer vision components built on Keras 3 that work natively with TensorFlow, JAX, or PyTorch. It provide… | 10 | 1055 | maintenance |
| microsoft/Cognitive-Samples-IntelligentKiosk A UWP sample application from Microsoft showcasing hands-free kiosk-style demos built on Azure Cognitive Services (Face, Computer Vision, T… | 10 | 1055 | maintenance |
| ashkamath/mdetr MDETR (Modulated Detection) is a PyTorch research codebase for end-to-end multi-modal object detection that grounds free-form text queries … | 32 | 1054 | maintenance |
| Talking Head Anime from a Single Image Demo programs for the Talking Head(?) Anime 3 project, which animates an anime character from a single image using machine learning. It inc… | 32 | 1045 | maintenance |
| haltakov/natural-language-image-search A demo application that searches Unsplash photos using natural language descriptions, powered by OpenAI's CLIP model over the ~2M photo Uns… | 23 | 1045 | maintenance |
| YuwenXiong/py-R-FCN A Python implementation of R-FCN (Region-based Fully Convolutional Networks) for object detection, modified from the official MATLAB code a… | 32 | 1044 | maintenance |
| jayrambhia/Install-OpenCV A collection of shell scripts that automate installing various versions of OpenCV on different Linux distributions such as Ubuntu, RedHat, … | 32 | 1044 | maintenance |
| juliuscanute/qr_code_scanner A Flutter plugin that embeds a native QR code and barcode scanner view on iOS and Android, returning scanned text and barcode format to Dar… | 23 | 1043 | maintenance |
| CalciferZh/minimal-hand A Python library for real-time 3D hand motion capture from a single RGB camera, running at over 100fps. It combines a deep network (DetNet)… | 23 | 1043 | maintenance |
| asingh33/CNNGestureRecognizer A desktop application that recognizes hand gestures from webcam video using a convolutional neural network built with Keras, TensorFlow/The… | 57 | 1042 | maintenance |
| SysCV/sam-pt SAM-PT extends the Segment Anything Model to zero-shot video segmentation by combining SAM with sparse point-based tracking (PIPS, CoTracke… | 29 | 1042 | maintenance |
| google-research/deeplab2 DeepLab2 is a TensorFlow library from Google Research providing a unified, state-of-the-art codebase for dense pixel labeling tasks such as… | 10 | 1038 | maintenance |
| hyye/lio-mapping A C++/ROS implementation of tightly coupled 3D lidar-inertial odometry and mapping (LIO-mapping), published at ICRA 2019. It jointly optimi… | 32 | 1032 | maintenance |
| ClementPinard/SfmLearner-Pytorch A PyTorch reimplementation of SfMLearner (Zhou et al., CVPR 2017), which jointly learns monocular depth estimation and camera ego-motion fr… | 63 | 1031 | maintenance |
| EdgeCrafter DEIMv2 is a real-time object detection framework that extends the DEIM DETR family with DINOv3-pretrained and distilled backbones plus a Sp… | 59 | 364 | active |
| xingyizhou/ExtremeNet Official PyTorch implementation of ExtremeNet, a CVPR 2019 bottom-up object detection method that detects four extreme points and one cente… | 32 | 1030 | maintenance |
| lmb-freiburg/flownet2 A Caffe fork implementing FlowNet 2.0, a deep CNN for optical flow estimation from image pairs, released with the CVPR 2017 paper. It inclu… | 32 | 1026 | maintenance |
| dwofk/fast-depth FastDepth is the official PyTorch implementation of the ICRA 2019 paper 'FastDepth: Fast Monocular Depth Estimation on Embedded Systems' fr… | 32 | 1026 | maintenance |
| koide3/hdl_localization A ROS package for real-time 3D localization using 3D LIDARs such as Velodyne HDL32e and VLP16. It performs UKF-based pose estimation with I… | 32 | 1026 | maintenance |
| edvardHua/PoseEstimationForMobile A TensorFlow-based library implementing CPM and Hourglass models with MobileNetV2 inverted residual modules for real-time single-person hum… | 32 | 1025 | maintenance |
| neeru1207/AI_Sudoku A Python desktop application with a Tkinter GUI that extracts a Sudoku puzzle from a photo using OpenCV image processing and solves it. Dig… | 32 | 1020 | maintenance |
| PRBonn/semantic_suma SuMa++ is a C++ implementation of efficient LiDAR-based semantic SLAM that builds 3D semantic maps from laser range scans, combining the Su… | 32 | 1019 | maintenance |
| wywu/LAB Official C++/Caffe implementation of the CVPR 2018 paper 'Look at Boundary: A Boundary-Aware Face Alignment Algorithm', which localizes fac… | 32 | 1018 | maintenance |
| rmislam/PythonSIFT A pure Python/NumPy implementation of SIFT (Scale-Invariant Feature Transform) that returns OpenCV KeyPoint objects and descriptors, making… | 45 | 1017 | maintenance |
| RyanZotti/Self-Driving-Car A hobby project that turns a toy Ferrari into a self-driving car using a Raspberry Pi, a PS3 controller for data collection, and a locally-… | 32 | 1017 | maintenance |
| trishume/eyeLike eyeLike is an OpenCV-based C++ implementation of Fabian Timm's gradient-based eye center localization algorithm for webcam pupil tracking. … | 32 | 1014 | maintenance |
| FaceTracker ofxFaceTracker is an openFrameworks addon for real-time non-rigid face tracking, based on Jason Saragih's FaceTracker C++ library and OpenC… | 10 | 1014 | maintenance |
| wpeebles/gangealing Official PyTorch implementation of GANgealing, a CVPR 2022 method that trains a Spatial Transformer to densely align images using GAN-gener… | 32 | 1013 | maintenance |
| zju3dv/OnePose OnePose is the official PyTorch implementation of the CVPR 2022 paper 'One-Shot Object Pose Estimation without CAD Models'. It estimates th… | 32 | 1011 | maintenance |
| bubbliiiing/yolov8-pytorch A PyTorch implementation of the YOLOv8 object detection model with training, prediction, and evaluation scripts. It supports training on cu… | 22 | 1011 | maintenance |
| mbrossar/ai-imu-dr Python/PyTorch implementation of the AI-IMU dead reckoning algorithm from the authors' IEEE/ArXiv paper, combining an invariant Kalman filt… | 32 | 1008 | maintenance |
| mileyan/pseudo_lidar Research code implementing Pseudo-LiDAR, a CVPR 2019 method that converts image-based depth maps into pseudo-LiDAR point clouds for 3D obje… | 32 | 1007 | maintenance |
| PeterWang512/CNNDetection A PyTorch research codebase with pretrained models for detecting CNN-generated (GAN/synthetic) images, from the CVPR 2020 paper 'CNN-genera… | 32 | 1006 | maintenance |
| alex04072000/ObstructionRemoval The official TensorFlow implementation of the CVPR 2020 paper 'Learning to See Through Obstructions', which removes obstructions like windo… | 32 | 1005 | maintenance |
| 1bananachicken/MaaNTE MaaNTE is an open-source automatic assistant for the game Neverness to Everness (NTE), built on MaaFramework. It recognizes the game screen… | 80 | 2823 | experimental |
| PiLiDAR PiLiDAR is a DIY 360° 3D panorama scanner built on Raspberry Pi that combines a low-cost LDRobot LiDAR (LD06/LD19/STL27L) with a Pi HQ came… | 56 | 1977 | experimental |
| everythingishacked/Semaphore Semaphore is a Python application that turns your full body into a keyboard using flag semaphore gestures. It uses OpenCV and MediaPipe pos… | 31 | 1940 | experimental |
| matthewearl/deep-anpr An experimental Python project that uses neural networks (TensorFlow) to build an automatic number plate recognition (ANPR) system. It incl… | 32 | 1860 | experimental |
| Anything-of-anything/Anything-3D Anything-3D is a Python research project that combines Meta's Segment Anything model with a series of 3D models (3DFuse, Zero 1-to-3, NeRF,… | 30 | 1633 | experimental |
| Ildaron/Laser_control An open-source hardware and software project that uses a camera, deep learning object detection (Darknet/YOLO via OpenCV), and galvanometer… | 62 | 1625 | experimental |
| OpnTec/mvisc MVISC (Mobile Visual Classification) is an application that identifies and classifies individual animals from photos using computer vision,… | 32 | 1384 | experimental |
| farzaa/gemini-bball A demo project from a viral tweet that uses Google's Gemini API to analyze basketball video frames, with an OpenCV-based visualizer. The co… | 29 | 1163 | experimental |
| geohot/twitchslam A toy monocular SLAM (Simultaneous Localization and Mapping) implementation written in Python during livestreams. It extracts features from… | 32 | 1003 | experimental |
| facebookresearch/Detectron Facebook AI Research's Python software system implementing state-of-the-art object detection algorithms such as Mask R-CNN, RetinaNet, and … | 10 | 26352 | abandoned |
| HumanSignal/labelImg LabelImg is a graphical image annotation tool written in Python with a Qt interface for drawing bounding boxes on images. It saves annotati… | 10 | 25043 | abandoned |
| wangshub/wechat_jump_game A Python script that plays the WeChat mini-game 'Jump Jump' (跳一跳) automatically by capturing Android screenshots via ADB, using image recog… | 23 | 13840 | abandoned |
| facebookresearch/AnimatedDrawings A Python tool from Meta AI that automatically animates children's drawings of human figures, implementing the algorithm from the paper 'A M… | 10 | 12808 | abandoned |
| react-native-camera/react-native-camera A camera component library for React Native providing photo/video capture, barcode scanning, and face detection. It is now deprecated in fa… | 10 | 9631 | abandoned |
| tracking.js tracking.js is a lightweight (~7 KB core) JavaScript library that brings computer vision algorithms like color tracking, object tracking, a… | 63 | 9460 | abandoned |
| facebookresearch/maskrcnn-benchmark A fast, modular PyTorch reference implementation of instance segmentation and object detection algorithms including Mask R-CNN, Faster R-CN… | 10 | 9361 | abandoned |
| rbgirshick/py-faster-rcnn A Python reimplementation of the Faster R-CNN object detection model built on a fork of Fast R-CNN and Caffe. The repository is officially … | 32 | 8289 | abandoned |
| jwyang/faster-rcnn.pytorch A pure PyTorch implementation of Faster R-CNN for object detection, supporting multi-image batch training and multi-GPU training with sever… | 32 | 7859 | abandoned |
| HannahMitt/HomeMirror An Android application that turns an Android tablet mounted behind a two-way mirror into a smart mirror displaying time, weather, calendar … | 32 | 7805 | abandoned |
| facebookresearch/DensePose DensePose is a research library from Facebook AI that maps all human pixels in 2D RGB images to a 3D surface-based model of the human body … | 10 | 7261 | abandoned |
| Hironsan/BossSensor A desktop application that uses a webcam and a trained CNN classifier to detect when a specific person (your boss) approaches, automaticall… | 32 | 6290 | abandoned |
| yahoo/open_nsfw A Python library from Yahoo that runs a Caffe deep neural network to classify images as Not Suitable for Work (NSFW), outputting a probabil… | 10 | 6014 | abandoned |
| paz A Python project providing real-time face detection with emotion and gender classification using a Keras CNN trained on fer2013 and IMDB da… | 32 | 5735 | abandoned |
| barcodescanner Android library projects providing easy-to-use, extensible barcode scanner views based on ZXing and ZBar. It wraps camera preview and decod… | 10 | 5427 | abandoned |
| landing-ai/vision-agent VisionAgent is a Python library from LandingAI that takes a natural-language prompt plus an image or video and automatically selects approp… | 51 | 5301 | abandoned |
| justadudewhohacks/opencv4nodejs Node.js bindings to the native OpenCV 3 and OpenCV 4 libraries, including OpenCV-contrib modules, with both synchronous and asynchronous AP… | 23 | 5053 | abandoned |
| accord-net/framework Accord.NET is a C# framework for .NET providing machine learning, statistics, computer vision, image and audio processing, and general scie… | 10 | 4531 | abandoned |
| RetinaNet (Keras/TF implementation) A Keras/TensorFlow implementation of the RetinaNet object detection model with focal loss, supporting training and inference on custom data… | 23 | 4382 | abandoned |
| mapillary/OpenSfM OpenSfM is a Python Structure-from-Motion library that reconstructs camera poses and 3D scenes from multiple images, including feature dete… | 68 | 3808 | abandoned |
| endernewton/tf-faster-rcnn A TensorFlow implementation of the Faster R-CNN object detection framework, supporting VGG16, ResNet, and MobileNet backbones trained and e… | 23 | 3649 | abandoned |
| rbgirshick/fast-rcnn Fast R-CNN is Ross Girshick's ICCV 2015 framework for fast object detection with deep convolutional networks, written in Python and C++/Caf… | 32 | 3462 | abandoned |
| bijection/sistine Project Sistine is a proof-of-concept Python application that turns a MacBook into a touchscreen using a $1 mirror rig in front of the buil… | 32 | 3430 | abandoned |
| OculiX SikuliX1 is the historical Java-based visual automation tool that uses OpenCV image recognition to locate on-screen GUI elements and drive … | 72 | 3246 | abandoned |
| neuralmagic/deepsparse DeepSparse is a sparsity-aware deep learning inference runtime that delivers GPU-class performance on x86 CPUs for ONNX models, covering co… | 10 | 3157 | abandoned |
| facebookresearch/deepmask A Torch (Lua) implementation of the DeepMask and SharpMask object proposal algorithms from Facebook AI Research. It generates class-agnosti… | 10 | 3097 | abandoned |
| CharlesShang/FastMaskRCNN A TensorFlow implementation of Mask R-CNN for instance segmentation, reproducing the paper by Kaiming He et al. It includes ROIAlign, a COC… | 32 | 3082 | abandoned |
| xdspacelab/openvslam OpenVSLAM is a versatile visual SLAM (Simultaneous Localization and Mapping) framework supporting monocular, stereo, and RGBD cameras, incl… | 10 | 2976 | abandoned |
| jetpacapp/DeepBeliefSDK Jetpac's Deep Belief SDK, a cross-platform image recognition framework implementing the AlexNet convolutional neural network architecture, … | 32 | 2851 | abandoned |
| isl-org/ZoeDepth ZoeDepth is a PyTorch library implementing metric depth estimation from a single image, combining relative and metric depth approaches with… | 10 | 2838 | abandoned |
| ShaoqingRen/faster_rcnn A MATLAB re-implementation of Faster R-CNN, a deep-learning object detection framework combining a Region Proposal Network with a detection… | 32 | 2835 | abandoned |
| Ownphotos Ownphotos is a self-hosted Google Photos alternative built with a Django backend and React frontend, offering face recognition, object dete… | 23 | 2757 | abandoned |
| SimpleCV SimpleCV is an open-source Python framework that wraps OpenCV and other vision libraries behind a simple, readable API for cameras, image m… | 32 | 2731 | abandoned |
| cloud-annotations/cloud-annotations Cloud Annotations is a collaborative open-source image annotation tool for creating labeled training datasets for object detection and clas… | 23 | 2677 | abandoned |
| Guikunzhi/BeautifyFaceDemo An iOS demo app showing realtime face beautification using a custom GPUImageBeautifyFilter built on the GPUImage framework. It can be appli… | 32 | 2471 | abandoned |
| lgsvl/simulator SVL Simulator is a Unity-based multi-robot simulator for autonomous vehicles with ROS/ROS2 integration, sensor simulation, and Python APIs.… | 23 | 2459 | abandoned |
| rbgirshick/rcnn The original R-CNN (Region-based Convolutional Neural Networks) object detection system from UC Berkeley, released as research code accompa… | 23 | 2416 | abandoned |
| karanchahal/DoodleMaster Doodle Master is a proof-of-concept AI tool that turns hand-drawn UI mockups into real HTML/CSS code using a CNN classifier for detecting U… | 32 | 2408 | abandoned |
| tryolabs/luminoth Luminoth is an open-source Python toolkit for computer vision built on TensorFlow and Sonnet, focused on object detection with Faster R-CNN… | 23 | 2406 | abandoned |
| pa7/nude.js nude.js is a client-side JavaScript nudity detection library that analyzes image data via HTMLCanvas using algorithms based on research pap… | 32 | 2357 | abandoned |
| microsoft/Deep3DFaceReconstruction A TensorFlow implementation of a weakly-supervised CNN method for reconstructing accurate 3D face models (shape, texture, pose, landmarks) … | 32 | 2357 | abandoned |
| colmap/glomap GLOMAP is a global structure-from-motion pipeline for image-based 3D reconstruction that takes a COLMAP database as input and outputs a COL… | 10 | 2351 | abandoned |
| isl-org/DPT DPT (Dense Prediction Transformers) is Intel's implementation of Vision Transformers for dense prediction tasks, providing pretrained model… | 10 | 2330 | abandoned |
| card.io card.io is an iOS SDK that provides fast, easy credit card number scanning using the device camera in mobile apps. It ships as a static lib… | 10 | 2288 | abandoned |
| kongqw/OpenCVForAndroid An Android sample library built on OpenCV 3.2.0 demonstrating object detection (face, eyes, smile, body), object tracking with the CamShift… | 32 | 2236 | abandoned |
| rmtheis/android-ocr An experimental Android app that performs optical character recognition on images captured with the device camera, running the Tesseract OC… | 10 | 2227 | abandoned |
| facebookarchive/Surround360 Facebook's open-source hardware and software system for capturing and rendering stereoscopic 3D 360-degree video for VR viewing. It include… | 10 | 2185 | abandoned |
| handtracking-io/yoha Yoha is a browser-based hand tracking engine built on TensorFlow.js that detects 21 2D hand landmarks, hand presence, left/right orientatio… | 23 | 2122 | abandoned |
| zk00006/OpenTLD OpenTLD (Predator) is a MATLAB implementation of the Tracking-Learning-Detection algorithm for real-time 2D tracking of a single unknown ob… | 32 | 2102 | abandoned |
| mapbox/robosat RoboSat is an end-to-end Python pipeline for semantic segmentation and feature extraction from aerial and satellite imagery, identifying fe… | 59 | 2065 | abandoned |
| moaazsidat/react-native-qrcode-scanner A plug-and-play QR code scanner component for React Native, built on top of react-native-camera, that also works as a generic barcode scann… | 10 | 2032 | abandoned |
| card.io card.io is an Android SDK that provides fast credit card scanning using the device camera, with OCR-based number recognition and a manual e… | 10 | 1993 | abandoned |