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 |
|---|---|---|---|
| dlbeer/quirc Quirc is a small, dependency-free C library for extracting and decoding QR codes from images, fast enough for realtime video. It handles ro… | 39 | 1011 | active |
| eragonruan/text-detection-ctpn A TensorFlow implementation of the Connectionist Text Proposal Network (CTPN) for detecting horizontal scene text in images. It includes pr… | 23 | 3427 | maintenance |
| facebookresearch/Mask2Former Mask2Former is the official PyTorch implementation of the CVPR 2022 paper 'Masked-attention Mask Transformer for Universal Image Segmentati… | 10 | 3417 | maintenance |
| shaoshengsong/DeepSORT A real-time multi-object tracking application in C++17 using Qt 6, OpenCV, and ONNX Runtime, running YOLO detection with four pluggable tra… | 83 | 1008 | active |
| SparseDrive SparseDrive is a research codebase implementing an end-to-end autonomous driving framework based on sparse scene representation. It unifies… | 58 | 1006 | active |
| clovaai/CRAFT-pytorch Official PyTorch implementation of CRAFT (Character Region Awareness for Text Detection), a scene text detector that localizes text by pred… | 32 | 3406 | maintenance |
| henry123-boy/SpaTrackerV2 SpatialTrackerV2 is a research library from ICCV 2025 that performs 3D point tracking in videos, lifting tracked points into 3D using depth… | 47 | 1005 | active |
| Image Captioning A PyTorch research codebase for image captioning, serving as the widely used unofficial implementation of Self-critical Sequence Training (… | 23 | 999 | stable |
| ViewFaceCore/ViewFaceCore ViewFaceCore is an easy-to-use offline face recognition library for .NET, built on top of SeetaFace6. It is open source, free, and cross-pl… | 32 | 998 | active |
| mit-han-lab/efficientvit A collection of efficient vision foundation models from MIT Han Lab, including EfficientViT backbones for perception, EfficientViT-SAM for … | 45 | 3361 | maintenance |
| hamuchiwa/AutoRCCar An open-source project that turns a hobby RC car into an autonomous self-driving vehicle using a Raspberry Pi, Arduino, camera, and ultraso… | 32 | 3351 | maintenance |
| shelhamer/fcn.berkeleyvision.org Reference implementation of Fully Convolutional Networks (FCN) for semantic segmentation from the CVPR 2015 / PAMI 2016 papers, built on Ca… | 32 | 3350 | maintenance |
| tianzhi0549/FCOS Official PyTorch implementation of FCOS, a fully convolutional one-stage, anchor-free object detector published at ICCV 2019. It provides t… | 32 | 3344 | maintenance |
| HRNet/HRNet-Semantic-Segmentation Official PyTorch implementation of HRNet (High-Resolution Network) and the Segmentation Transformer (OCR) approach for semantic segmentatio… | 32 | 3337 | maintenance |
| pytorch-yolo-v3 A minimal PyTorch implementation of the YOLO v3 object detection algorithm, supporting detection on images and video with configurable reso… | 32 | 3314 | maintenance |
| NVIDIA/flownet2-pytorch A PyTorch implementation of FlowNet 2.0 for deep-learning-based optical flow estimation, released by NVIDIA. It provides multiple network a… | 62 | 3292 | maintenance |
| anandpawara/Real_Time_Image_Animation A real-time Python application that animates a still image (e.g., a portrait) using facial motion from a live camera or video file, built o… | 32 | 3246 | maintenance |
| LBXScan LBXScan is an iOS barcode and QR code scanning library that wraps the native AVFoundation API, ZXing, and ZBar engines behind a unified int… | 32 | 3238 | maintenance |
| thearn/webcam-pulse-detector A Python desktop application that estimates a person's heart rate in real time using only a webcam, by analyzing subtle color intensity cha… | 38 | 3232 | maintenance |
| UVCCamera An Android library (with sample apps) that lets non-rooted Android devices access UVC USB web cameras via native code built on libuvc/libus… | 32 | 3218 | maintenance |
| mkocabas/VIBE Official PyTorch implementation of VIBE (CVPR 2020), a video-based method for 3D human body pose and shape estimation that predicts SMPL bo… | 23 | 3210 | maintenance |
| MaximeBeasse/KeyDecoder KeyDecoder is a Flutter mobile app that lets pentesters and security enthusiasts measure the bitting of a mechanical key from a photo, usin… | 23 | 3196 | maintenance |
| tinyvision/DAMO-YOLO DAMO-YOLO is a fast and accurate object detection framework built on PyTorch, featuring NAS-searched backbones, RepGFPN, a lightweight Zero… | 32 | 3193 | maintenance |
| Habitat AI Habitat is a high-performance, physics-enabled 3D simulation platform for Embodied AI research, consisting of Habitat-Sim (a fast 3D sim… | 68 | 3159 | maintenance |
| open-mmlab/mmskeleton MMSkeleton is an OpenMMLAB toolbox for skeleton-based human understanding, built on PyTorch. It supports 2D pose estimation, skeleton-based… | 23 | 3131 | maintenance |
| lucasjinreal/yolov7_d2 A detectron2-based implementation of YOLOv7 that extends YOLO-style detection to instance segmentation, keypoint detection, and multi-head … | 23 | 3112 | maintenance |
| tusen-ai/simpledet SimpleDet is a Python framework built on MXNet for object detection and instance recognition. It provides state-of-the-art detection models… | 32 | 3085 | maintenance |
| argman/EAST A TensorFlow re-implementation of the EAST (Efficient and Accurate Scene Text Detector) deep learning model for detecting text in natural s… | 32 | 3056 | maintenance |
| schmich/instascan Instascan is a JavaScript library that provides real-time QR code scanning from a webcam feed in the browser, built on top of ZXing compile… | 23 | 3022 | maintenance |
| microsoft/human-pose-estimation.pytorch Official PyTorch implementation of the ECCV 2018 paper 'Simple Baselines for Human Pose Estimation and Tracking' from Microsoft. It provide… | 10 | 3005 | maintenance |
| divamgupta/image-segmentation-keras A Keras library implementing popular deep learning semantic image segmentation models including SegNet, FCN, U-Net, and PSPNet. It provides… | 23 | 3002 | maintenance |
| BeauNouvelle/FaceAware A Swift extension for UIImageView on iOS that detects faces in an image and adjusts the view's focus so faces stay visible when aspect-fill… | 10 | 2994 | maintenance |
| biubug6/Pytorch_Retinaface A PyTorch implementation of the RetinaFace single-stage face detection model, supporting mobilenet0.25 and resnet50 backbones with pretrain… | 32 | 2976 | maintenance |
| Tencent/FaceDetection-DSFD DSFD (Dual Shot Face Detector) is Tencent Youtu's high-accuracy face detection network, released with PyTorch inference code and pretrained… | 52 | 2975 | maintenance |
| Cartucho/mAP A Python library and script that computes mean Average Precision (mAP) for object detection models, adapted from the official PASCAL VOC 20… | 23 | 2970 | maintenance |
| CainKernel/CainCamera An open-source Android app and set of libraries demonstrating how to build a beauty camera, image editor, and short-video editor. It implem… | 32 | 2966 | maintenance |
| NVIDIA/MinkowskiEngine Minkowski Engine is an auto-differentiation neural network library for high-dimensional sparse tensors, built on PyTorch with CUDA accelera… | 23 | 2960 | maintenance |
| xiaofengShi/CHINESE-OCR An end-to-end Chinese scene-text OCR pipeline combining CTPN for text detection, a VGG16-based orientation classifier, and CRNN with CTC fo… | 73 | 2956 | maintenance |
| ZXing JavaScript ZXing TypeScript is an open-source, multi-format 1D/2D barcode image processing library ported from the Java ZXing project. It can decode b… | 90 | 2939 | maintenance |
| Handtrack.js Hand Detection Handtrack.js is a JavaScript library for prototyping realtime hand detection directly in the browser, framing handtracking as an object det… | 23 | 2931 | maintenance |
| zhaipro/easy12306 A Python project that uses deep learning models to automatically recognize 12306 (China Railway) captchas, identifying both the Chinese tex… | 23 | 2911 | maintenance |
| biometrics/openbr OpenBR is an open-source biometrics library and command-line tool focused on face recognition, written in C++ on top of Qt and OpenCV. It p… | 47 | 2900 | maintenance |
| ethz-asl/maplab maplab 2.0 is an open, research-oriented C++ mapping framework for multi-session and multi-robot SLAM, built on ROS. It provides robust vis… | 23 | 2880 | maintenance |
| kpzhang93/MTCNN_face_detection_alignment Reference MATLAB/Caffe implementation of MTCNN, a multi-task cascaded convolutional neural network for joint face detection and facial land… | 32 | 2863 | maintenance |
| IDEA-Research/DINO Official PyTorch implementation of DINO, a state-of-the-art end-to-end object detection model based on DETR with improved denoising anchor … | 32 | 2852 | maintenance |
| IDEA-Research/DWPose DWPose is the official implementation of 'Effective Whole-body Pose Estimation with Two-stages Distillation' (ICCV 2023), providing whole-b… | 29 | 2843 | maintenance |
| Starry-Wind/StarRailAssistant StarRailAssistant is a free, open-source automation tool for the game Honkai: Star Rail that automates gameplay such as resource farming ('… | 21 | 2812 | maintenance |
| roytseng-tw/Detectron.pytorch A PyTorch reimplementation of Facebook's Detectron object detection framework, supporting Mask R-CNN, keypoint/pose estimation, and instanc… | 10 | 2808 | maintenance |
| yfeng95/face3d A lightweight Python library implementing core 3D face processing functions: 3D morphable model (3DMM) generation and fitting, mesh I/O, tr… | 32 | 2779 | maintenance |
| YCG09/chinese_ocr An end-to-end Chinese OCR system implemented with TensorFlow and Keras, combining CTPN for text detection with DenseNet + CTC for text reco… | 32 | 2776 | maintenance |
| inspirit/jsfeat JSFEAT is a JavaScript computer vision library implementing classic CV algorithms in pure JS for browser use. It includes image processing … | 23 | 2771 | maintenance |
| LeGO-LOAM LeGO-LOAM is a lightweight, ground-optimized lidar odometry and mapping (SLAM) system for ROS-compatible unmanned ground vehicles. It consu… | 32 | 2754 | maintenance |
| tum-vision/lsd_slam LSD-SLAM is a real-time monocular SLAM system that uses direct (featureless) image alignment to build large-scale, semi-dense 3D maps from … | 32 | 2730 | maintenance |
| vchoutas/smplx A PyTorch implementation of SMPL-X, a unified parametric 3D model of the human body with fully articulated hands and an expressive face, al… | 32 | 2720 | maintenance |
| torch-points3d/torch-points3d A PyTorch-based framework for deep learning on 3D point clouds, supporting models like PointNet, KPConv, and MinkowskiEngine sparse convolu… | 64 | 2717 | maintenance |
| zllrunning/video-object-removal A PyTorch application that removes objects from videos by drawing a bounding box around them. It combines SiamMask for object tracking and … | 32 | 2714 | maintenance |
| Tencent/GameAISDK Tencent's aitest is an open-source toolkit for building game AI based on game images, providing UI detection, in-game element recognition, … | 23 | 2697 | maintenance |
| mahyarnajibi/SNIPER SNIPER is an efficient multi-scale training algorithm for object detection and instance segmentation that processes only context regions (c… | 32 | 2692 | maintenance |
| AR Cut & Paste An AR+ML research prototype that lets users capture objects from their physical surroundings with a phone camera and paste them into Photos… | 32 | 14561 | experimental |
| KupynOrest/DeblurGAN A PyTorch implementation of the DeblurGAN paper for blind motion deblurring using conditional adversarial networks. It uses a Conditional W… | 32 | 2639 | maintenance |
| PeterH0323/Smart_Construction A YOLOv5-based object detection application for detecting people, heads, and safety helmets on construction sites, including pretrained wei… | 23 | 2628 | maintenance |
| linyiLYi/pose-monitor An Android app that uses the camera to detect bad sitting posture in real time and gives voice reminders. It runs MoveNet pose estimation p… | 23 | 2624 | maintenance |
| knazeri/edge-connect EdgeConnect is a PyTorch implementation of a two-stage generative adversarial model for image inpainting, published at ICCV 2019. It first … | 32 | 2622 | maintenance |
| microsoft/GLIP GLIP is Microsoft's official implementation of Grounded Language-Image Pre-training, a vision-language model that unifies object detection … | 32 | 2612 | maintenance |
| fSpy fSpy is an open source, cross-platform desktop app for still image camera matching, computing camera parameters from a reference image. It … | 23 | 2601 | maintenance |
| baaivision/Painter Painter and SegGPT are vision foundation models from BAAI for in-context visual learning, where a single generalist model performs diverse … | 32 | 2598 | maintenance |
| zllrunning/face-parsing.PyTorch A PyTorch implementation of face parsing using a modified BiSeNet architecture, trained on the CelebAMask-HQ dataset. It provides training … | 32 | 2590 | maintenance |
| iliasam/OpenSimpleLidar Open Source scanning laser rangefinder (lidar) built with STM32 firmware and a triangulation-based optical design, with schematics, firmwar… | 34 | 2571 | maintenance |
| MaybeShewill-CV/lanenet-lane-detection An unofficial TensorFlow implementation of the LaneNet deep neural network for real-time lane detection, based on the IEEE IV paper 'Toward… | 32 | 2564 | maintenance |
| ZBar/ZBar ZBar is an open-source C library and software suite for reading bar codes from video streams, image files, and raw intensity sensors. It su… | 32 | 2541 | maintenance |
| LazoVelko/Windows-Hacks A Windows application showcasing creative and unusual manipulations of other windows via the Windows API, written in C#. It includes tricks… | 32 | 2539 | maintenance |
| yfeng95/DECA DECA is the official PyTorch implementation of a SIGGRAPH 2021 method that reconstructs a detailed 3D head model (pose, shape, facial detai… | 32 | 2524 | maintenance |
| zzh8829/yolov3-tf2 A clean implementation of YOLOv3 and YOLOv3-tiny object detection in TensorFlow 2.0, with pre-trained Darknet weight conversion, inference,… | 32 | 2513 | maintenance |
| galeone/tfgo tfgo is a Go library that wraps TensorFlow's Go bindings with a friendlier, method-chaining API for building and executing computation grap… | 32 | 2495 | maintenance |
| coneypo/Dlib_face_recognition_from_camera A Python application that performs real-time face detection and recognition from a webcam using Dlib's ResNet-34-based 128D descriptor mode… | 32 | 2482 | maintenance |
| ctripcorp/C-OCR C-OCR is Ctrip's in-house OCR project focused on recognizing travel-related documents such as ID cards, passports, train tickets, and visas… | 32 | 2477 | maintenance |
| xingyizhou/CenterTrack CenterTrack is a deep learning model and research codebase that performs simultaneous multi-object detection and tracking using center poin… | 32 | 2476 | maintenance |
| Direct Sparse Odometry DSO (Direct Sparse Odometry) is a C++ library implementing monocular visual odometry using direct sparse methods with photometric calibrati… | 32 | 2459 | maintenance |
| notAI-tech/NudeNet NudeNet is a lightweight Python library for nudity detection in images, built on YOLOv8 models running via ONNX Runtime. It detects exposed… | 58 | 2456 | maintenance |
| Zhongdao/Towards-Realtime-MOT A PyTorch codebase for the Joint Detection and Embedding (JDE) model, a fast multiple-object tracker that learns object detection and appea… | 32 | 2446 | maintenance |
| HKUST-Aerial-Robotics/A-LOAM A-LOAM is an advanced, simplified C++ implementation of LOAM (Lidar Odometry and Mapping in Real-time) built on Eigen and Ceres Solver. It … | 32 | 2446 | maintenance |
| leggedrobotics/darknet_ros A ROS package wrapping the YOLO (Darknet) real-time object detector for use in robotic systems. It subscribes to camera image topics and pu… | 23 | 2443 | maintenance |
| deepcam-cn/yolov5-face YOLOv5-Face is a real-time, high-accuracy face detector built on the YOLOv5 object detection framework in PyTorch, with TensorRT deployment… | 32 | 2411 | maintenance |
| Roujack/mathAI mathAI is a photo-based math problem solver written in Python: it takes an image containing a handwritten or printed arithmetic expression,… | 32 | 2372 | maintenance |
| princeton-vl/CornerNet Official research code for CornerNet, an object detection model that detects objects as paired keypoints, reproducing results from the ECCV… | 32 | 2369 | maintenance |
| sarxos/webcam-capture A Java library for accessing built-in or USB webcams (and MJPEG IP cameras) with a simple, thread-safe, driver-abstracted API. It includes … | 42 | 2356 | maintenance |
| smallcorgi/Faster-RCNN_TF A TensorFlow implementation of Faster R-CNN, a convolutional neural network for object detection with a region proposal network. It include… | 32 | 2341 | maintenance |
| koide3/hdl_graph_slam hdl_graph_slam is an open-source ROS package for real-time 6DOF SLAM using 3D LIDAR, based on graph SLAM with NDT scan matching odometry an… | 32 | 2337 | maintenance |
| OAID/TengineKit TengineKit is a mobile AI SDK by OPEN AI LAB providing real-time face detection, face 2D/3D landmarks, face attributes, iris, hand, and bod… | 23 | 2320 | maintenance |
| Hzzone/pytorch-openpose A PyTorch reimplementation of OpenPose for body and hand pose estimation, with models converted directly from the original OpenPose caffemo… | 32 | 2318 | maintenance |
| fudan-zvg/Semantic-Segment-Anything Semantic Segment Anything (SSA) is a Python framework that adds semantic category prediction to the Segment Anything Model (SAM) by combini… | 31 | 2304 | maintenance |
| Dynamic 3D Gaussians Official PyTorch implementation of 'Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis' (3DV 2024), which models dynamic 3… | 29 | 2303 | maintenance |
| facebookresearch/frankmocap FrankMocap is a single-view 3D motion capture system from Facebook AI Research that estimates 3D pose for body, hands, and whole body (body… | 10 | 2294 | maintenance |
| jsbroks/coco-annotator COCO Annotator is a web-based image annotation tool for labeling images with segments, bounding boxes, keypoints, and object tracking to cr… | 23 | 2286 | maintenance |
| zju3dv/NeuralRecon NeuralRecon is a deep learning framework for real-time 3D scene reconstruction from monocular video with known camera poses. It reconstruct… | 32 | 2284 | maintenance |
| qianqianwang68/omnimotion OmniMotion is a PyTorch implementation of the ICCV 2023 paper 'Tracking Everything Everywhere All at Once', which tracks every point in a v… | 30 | 2268 | maintenance |
| MhLiao/DB A PyTorch implementation of DBNet and DBNet++, real-time arbitrary-shape scene text detection models based on differentiable binarization. … | 32 | 2265 | maintenance |
| mrharicot/monodepth A TensorFlow implementation of unsupervised monocular depth estimation from single images using convolutional neural networks, based on the… | 32 | 2263 | maintenance |
| ShoufaChen/DiffusionDet PyTorch implementation of DiffusionDet, the first diffusion-model-based object detection framework (ICCV 2023 Best Paper Finalist). It prov… | 23 | 2259 | maintenance |
| hunglc007/tensorflow-yolov4-tflite A TensorFlow 2.x implementation of YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny object detection models, with scripts that convert original… | 32 | 2255 | maintenance |