Open-source computer-vision software
2359 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.
2359 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| cleardusk/3DDFA_V2 3DDFA_V2 is the official PyTorch implementation of the ECCV 2020 paper 'Towards Fast, Accurate and Stable 3D Dense Face Alignment'. It regr… | 23 | 3150 | stable |
| z-x-yang/Segment-and-Track-Anything An open-source pipeline (SAM-Track) that segments and tracks arbitrary objects in videos using the Segment Anything Model for key-frame seg… | 58 | 3140 | active |
| otiai10/gosseract gosseract is a Go package that provides OCR (Optical Character Recognition) by binding to the Tesseract C++ library via cgo. It lets Go app… | 47 | 3136 | active |
| OpenVINS OpenVINS is an open-source C++ platform for visual-inertial navigation research, centered on a filter-based (MSCKF/EKF) estimator that fuse… | 44 | 3121 | active |
| naver/mast3r MASt3R is the official PyTorch implementation of 'Grounding Image Matching in 3D with MASt3R' (ECCV 2024), a model that performs dense 3D r… | 34 | 3114 | active |
| junyanz/CycleGAN A Torch (Lua) implementation of CycleGAN and pix2pix for unpaired image-to-image translation using cycle-consistent adversarial networks. I… | 32 | 12874 | maintenance |
| QwenLM/Qwen-MM-Plugins A collection of native multimodal plugins (Skills plus optional MCP servers) for Qwen models that make any agent harness multimodal-native.… | 57 | 3110 | active |
| jina-ai/clip-as-service CLIP-as-service is a low-latency, high-scalability server for embedding images and text into fixed-length vectors using OpenAI's CLIP model… | 23 | 12831 | maintenance |
| SharpAI/DeepCamera DeepCamera is an open-source AI camera skills platform that runs local VLM scene analysis, object detection, face recognition, and person r… | 86 | 3075 | active |
| zxingify/zxingify-objc ZXingObjC is a full Objective-C port of the ZXing barcode image processing library, supporting encoding and decoding of many 1D and 2D barc… | 23 | 3074 | active |
| yuyuyzl/EasyVtuber EasyVtuber is a Python-based VTubing application built on the Talking Head Anime model that turns a single anime character illustration int… | 59 | 3071 | active |
| antimatter15/splat A WebGL-based real-time viewer for 3D Gaussian Splatting scenes, rendering photorealistic navigable 3D environments from photo-derived spla… | 48 | 3071 | active |
| AnyListen/tools-ocr Tree Hole OCR is a cross-platform desktop OCR tool built with Java and JavaFX that performs offline text recognition using Paddle OCR model… | 23 | 3063 | active |
| thiagoalessio/tesseract-ocr-for-php A PHP wrapper library around the Tesseract OCR command-line binary, providing a fluent API for extracting text from images. It supports mul… | 57 | 3043 | stable |
| ZQPei/deep_sort_pytorch A PyTorch implementation of the Deep SORT multi-object tracking algorithm, pairing YOLOv3/YOLOv5 (or Mask R-CNN) detectors with a CNN re-id… | 32 | 3013 | active |
| osmr/imgclsmob A research sandbox providing (re)implementations of numerous deep learning computer vision models for classification, segmentation, detecti… | 23 | 3012 | active |
| Doubiiu/DynamiCrafter DynamiCrafter is an open-source research model that animates open-domain still images into short videos using pre-trained video diffusion p… | 27 | 3005 | active |
| MeiGen-AI/MultiTalk MultiTalk is an audio-driven framework for generating multi-person conversational videos from multi-stream audio, a reference image, and a … | 53 | 3000 | active |
| williamyang1991/Rerender_A_Video The official PyTorch implementation of 'Rerender A Video', a SIGGRAPH Asia 2023 zero-shot text-guided video-to-video translation framework.… | 30 | 2997 | stable |
| zju3dv/LoFTR LoFTR is a detector-free local image feature matching method using Transformers, released with PyTorch inference and training code plus pre… | 32 | 2963 | stable |
| sunsmarterjie/yolov12 YOLOv12 is a PyTorch implementation of attention-centric real-time object detectors, published at NeurIPS 2025. It provides detection model… | 66 | 2961 | active |
| sherlockchou86/VideoPipe VideoPipe is a C++ framework for video analysis and structuring that works like a pipeline of independent, composable nodes. It integrates … | 50 | 2960 | active |
| microsoft/MoGe MoGe is a deep learning model from Microsoft Research that recovers 3D geometry from a single open-domain image, predicting metric point ma… | 65 | 2958 | active |
| iscyy/ultralyticsPro A PyTorch-based collection of improved YOLO-family object detection models (YOLOv5 through YOLOv13, RT-DETR) with pluggable modules for bac… | 45 | 2954 | active |
| ogkalu2/comic-translate An AI-powered application and browser extension that automatically translates comics, manga, manhwa, webtoons, and BDs across many language… | 89 | 2949 | active |
| jeeliz/jeelizFaceFilter A lightweight JavaScript/WebGL library for real-time face detection and tracking from a camera feed via WebRTC, designed for building augme… | 43 | 2949 | active |
| KichangKim/DeepDanbooru DeepDanbooru is a Python/TensorFlow system that estimates Danbooru-style tags for anime-style girl images using multi-label classification.… | 60 | 2948 | active |
| microsoft/table-transformer Table Transformer (TATR) is a deep learning object detection model from Microsoft for detecting, recognizing, and extracting tables from un… | 23 | 2948 | active |
| Kruk2/jasna Jasna is a GPU-accelerated tool that detects and restores mosaics in JAV videos and still images, with a native GUI, CLI, and streaming sup… | 84 | 2943 | active |
| xelatihy/yocto-gl Yocto/GL is a collection of small C++17 libraries for building physically-based graphics algorithms, written in a data-oriented style and r… | 23 | 2929 | active |
| Mitsuba 3 Mitsuba 3 is a research-oriented, retargetable rendering system for forward and inverse light transport simulation, written in C++17 on top… | 90 | 2928 | active |
| InternLM/InternLM-XComposer InternLM-XComposer is a family of large vision-language models from the InternLM team, including XComposer2.5 for long-context multimodal u… | 35 | 2927 | active |
| NVlabs/FoundationStereo FoundationStereo is NVIDIA's official PyTorch implementation of a foundation model for zero-shot stereo depth estimation, published as a CV… | 44 | 2923 | active |
| Open-Cascade-SAS/OCCT Open CASCADE Technology (OCCT) is an open-source C++ development platform for 3D surface and solid modeling, CAD data exchange, and visuali… | 88 | 2910 | stable |
| learnables/learn2learn learn2learn is a PyTorch library for meta-learning research, providing utilities for few-shot task creation, high-level wrappers for algori… | 45 | 2894 | active |
| nimiq/qr-scanner A lightweight JavaScript/TypeScript QR code scanner library based on Cosmo Wolfe's port of Google's ZXing library. It supports webcam video… | 32 | 2888 | stable |
| openmv/openmv OpenMV is an open-source machine vision platform consisting of camera hardware firmware programmable in Python 3 (MicroPython). The firmwar… | 93 | 2871 | active |
| gem5 gem5 is the official open-source computer-system architecture simulator for research and teaching, modeling processor microarchitecture and… | 86 | 2871 | active |
| UX-Decoder/Semantic-SAM Official PyTorch implementation of Semantic-SAM, a universal image segmentation model that segments and recognizes anything at any desired … | 30 | 2855 | active |
| OpenGVLab/InternImage InternImage is a large-scale CNN-based vision foundation model that uses deformable convolutions as its core operator, released with pretra… | 25 | 2854 | stable |
| JavaCV JavaCPP Presets provides Java bindings for commonly used native C++ libraries such as OpenCV, FFmpeg, and many others, built on the JavaCPP… | 84 | 2848 | active |
| google-research/kubric Kubric is a data generation pipeline from Google Research for creating semi-realistic synthetic multi-object videos with rich annotations l… | 57 | 2839 | active |
| openalpr/openalpr OpenALPR is an open-source Automatic License Plate Recognition (ALPR) library written in C++ that analyzes images and video streams to dete… | 23 | 11462 | maintenance |
| kha-white/manga-ocr Manga OCR is a Python library providing optical character recognition for Japanese text, focused on Japanese manga. It uses a custom end-to… | 77 | 2809 | stable |
| nutonomy/nuscenes-devkit The official Python devkit for the nuScenes dataset, a large-scale autonomous driving dataset from Motional. It provides dataset loading, v… | 62 | 2807 | stable |
| viser-project/viser Viser is a Python library for web-based 3D visualization aimed at computer vision and robotics. It provides APIs for rendering 3D primitive… | 96 | 2803 | active |
| rom1504/clip-retrieval A Python toolkit for computing CLIP embeddings for images and text and building a semantic search/retrieval system on top of them. It inclu… | 52 | 2797 | active |
| torinmb/mediapipe-touchdesigner A GPU-accelerated, self-contained MediaPipe plugin for TouchDesigner that runs MediaPipe vision models (face detection, face/hand/pose trac… | 83 | 2784 | active |
| Autodistill Autodistill is a Python library that uses large foundation vision models (like Grounding DINO, Grounded SAM, and CLIP) to automatically lab… | 64 | 2784 | active |
| imanoop7/Ollama-OCR A Python package and Streamlit web app that performs OCR on images and PDFs using vision language models served through Ollama. It supports… | 23 | 2780 | active |
| Mininglamp-AI/Mano-P Mano-P is an open-source GUI-VLA (vision-language-action) agent model and SDK for edge devices, enabling purely vision-driven cross-platfor… | 52 | 2779 | active |
| jiangdongguo/AndroidUSBCamera AUSBC (AndroidUSBCamera) is a flexible UVC (USB video class) camera engine for Android, refactored in Kotlin with native C components. It s… | 23 | 2766 | active |
| NVlabs/stylegan2 The official TensorFlow implementation of StyleGAN2, NVIDIA's improved style-based generative adversarial network for high-quality uncondit… | 32 | 11180 | maintenance |
| NVIDIA/FastPhotoStyle FastPhotoStyle is NVIDIA's official PyTorch implementation of the ECCV 2018 paper 'A Closed-form Solution to Photorealistic Image Stylizati… | 23 | 11171 | maintenance |
| apple/turicreate Turi Create is a Python library from Apple that simplifies building custom machine learning models for tasks like image classification, obj… | 10 | 11155 | maintenance |
| dynobo/normcap NormCap is an OCR-powered screen-capture application that lets users select a region of the screen and extracts its text to the clipboard i… | 67 | 2751 | active |
| stevenlovegrove/Pangolin Pangolin is a lightweight, portable C++ utility library for rapid prototyping of 3D, numeric, and video-based programs, providing cross-pla… | 81 | 2750 | stable |
| hiukim/mind-ar-js MindAR is a web augmented reality library supporting image tracking and face tracking, written end-to-end in JavaScript with TensorFlow.js.… | 23 | 2746 | active |
| infstellar/genshin_impact_assistant A multi-functional Genshin Impact auto-assist application that uses image recognition and simulated keystrokes to automate combat, domain r… | 10 | 2730 | active |
| CVCUDA/CV-CUDA CV-CUDA is an open-source GPU-accelerated library of computer vision and image processing operators built on CUDA, with C++ and Python APIs… | 92 | 2729 | active |
| lengstrom/fast-style-transfer A TensorFlow implementation of fast neural style transfer that applies the style of famous paintings to photos and videos in real time. It … | 32 | 10957 | maintenance |
| bmild/nerf The official TensorFlow implementation of NeRF (Neural Radiance Fields), the ECCV 2020 paper representing scenes as neural radiance fields … | 36 | 10944 | maintenance |
| IDEA-Research/T-Rex T-Rex is the official Python API client for T-Rex2, a generic open-set object detection model that combines text and visual prompts to dete… | 45 | 2711 | active |
| yuweihao/MambaOut MambaOut is a PyTorch implementation of Gated CNN models from the CVPR 2025 paper 'MambaOut: Do We Really Need Mamba for Vision?', which qu… | 16 | 2710 | stable |
| teslamotors/react-native-camera-kit A high-performance React Native camera library providing cross-platform camera capture, QR/barcode scanning, and face detection for iOS and… | 90 | 2707 | active |
| TMElyralab/MusePose MusePose is a diffusion-based, pose-guided image-to-video generation framework for creating virtual human videos, where a character in a re… | 25 | 2706 | active |
| magic-research/magic-animate MagicAnimate is the official implementation of a CVPR 2024 diffusion-based human image animation framework that animates a reference image … | 41 | 10889 | maintenance |
| HiLab-git/SSL4MIS A benchmark and code collection of semi-supervised learning methods for medical image segmentation, re-implementing approaches like Mean Te… | 40 | 2699 | active |
| princeton-vl/DROID-SLAM DROID-SLAM is a deep learning-based visual SLAM system for monocular, stereo, and RGB-D cameras that estimates camera trajectory and dense … | 38 | 2699 | active |
| jlblancoc/nanoflann nanoflann is a C++11 header-only library for fast nearest neighbor search using KD-trees. It is designed for efficient queries over point c… | 95 | 2697 | stable |
| roboflow/maestro maestro is a Python library from Roboflow that streamlines fine-tuning of multimodal vision-language models such as Florence-2, PaliGemma 2… | 61 | 2696 | active |
| baaivision/EVA EVA is a family of large-scale vision foundation models from BAAI, including masked image models (EVA-01/02) and scaled CLIP models (EVA-CL… | 23 | 2694 | active |
| tryolabs/norfair Norfair is a lightweight, customizable Python library for real-time multi-object tracking that works with any detector outputting (x, y) co… | 28 | 2689 | stable |
| JIA-Lab-research/LISA LISA (Large Language Instructed Segmentation Assistant) is a multimodal large language model that performs reasoning-based image segmentati… | 29 | 2687 | active |
| MrGiovanni/UNetPlusPlus Official implementation of UNet++, a nested U-Net architecture for medical image segmentation, in both Keras and PyTorch. It redesigns skip… | 73 | 2685 | stable |
| InfiniteYou InfiniteYou (InfU) is a research framework from ByteDance for identity-preserved text-to-image generation built on Diffusion Transformers l… | 34 | 2685 | active |
| Tencent-Hunyuan/HY-World-2.0 HY-World 2.0 is Tencent Hunyuan's open-source multi-modal world model framework that reconstructs, generates, and simulates 3D worlds from … | 55 | 2680 | active |
| LAM LHM is a PyTorch-based large reconstruction model that reconstructs high-fidelity animatable 3D human avatars from a single image in second… | 49 | 2679 | active |
| StableSR StableSR is a Python research library that leverages pre-trained Stable Diffusion priors for real-world blind image super-resolution. It pr… | 21 | 2672 | stable |
| Tencent/MimicMotion MimicMotion is a diffusion-based framework from Tencent for generating high-quality human motion videos guided by pose sequences, featuring… | 44 | 2668 | active |
| om-ai-lab/OmAgent OmAgent is a Python library for building multimodal language agents, wrapping worker orchestration, task queues, and graph-based workflow o… | 28 | 2667 | active |
| Colour Colour is an open-source Python library providing a comprehensive collection of colour science algorithms and datasets, including colour sp… | 71 | 2663 | active |
| phillipi/pix2pix The original Torch (Lua) implementation of pix2pix, a conditional GAN for image-to-image translation tasks such as synthesizing photos from… | 32 | 10659 | maintenance |
| FeatherTalk An ultralight talking-head (digital human) model that animates a person's face from audio input and runs in real time on mobile devices. It… | 61 | 2648 | active |
| swz30/Restormer Restormer is an efficient Transformer architecture for high-resolution image restoration, published as a CVPR 2022 Oral paper. It provides … | 41 | 2648 | stable |
| 3D Slicer 3D Slicer is a free, open-source desktop platform for visualization, processing, segmentation, registration, and analysis of medical and bi… | 67 | 2644 | stable |
| kavan010/black_hole A C++ black hole simulation that uses ray tracing and GPU compute shaders to render gravitational lensing, accretion disks, and spacetime c… | 51 | 2643 | active |
| ultralytics/yolov3 Ultralytics' PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection. It provides training, validation… | 66 | 10613 | maintenance |
| antoinelame/GazeTracking A Python library that provides webcam-based eye tracking, returning pupil coordinates and gaze direction in real time using OpenCV and dlib… | 64 | 2634 | active |
| OpenStitching/stitching A Python package providing fast and robust image stitching to create panoramas, built on OpenCV's stitching module. It offers both a Python… | 94 | 2627 | active |
| luca-medeiros/lang-segment-anything A Python library combining Meta's Segment Anything Model 2 with GroundingDINO to generate segmentation masks for objects in images specifie… | 35 | 2600 | active |
| Intent-Lab/VisionClaw VisionClaw is a real-time AI assistant app for Meta Ray-Ban smart glasses that streams camera frames and microphone audio to the Gemini Liv… | 59 | 2591 | active |
| jpcy/xatlas xatlas is a small C++11 library with no external dependencies that generates unique texture coordinates (UV unwrapping) for 3D meshes. It i… | 32 | 2582 | stable |
| advimman/lama LaMa is a PyTorch-based image inpainting model that fills large missing regions in images using fast Fourier convolutions, generalizing wel… | 32 | 10291 | maintenance |
| raulmur/ORB_SLAM2 ORB-SLAM2 is a real-time SLAM library for monocular, stereo, and RGB-D cameras that computes camera trajectories and sparse 3D reconstructi… | 32 | 10245 | maintenance |
| BrunoLevy/geogram Geogram is a C++ programming library of geometric algorithms for geometry processing, including surface reconstruction, remeshing, Boolean … | 93 | 2558 | stable |
| DeepDetect DeepDetect is an open-source deep learning runtime, CLI, and REST server written in C++ for training and inference across images, text, tab… | 95 | 2551 | active |
| AprilTag AprilTag is a small C library implementing a visual fiducial (marker) detection system, computing the precise 3D position, orientation, and… | 65 | 2548 | stable |
| X-PLUG/mPLUG-Owl mPLUG-Owl is a family of open-source multimodal large language models that combine visual encoders with LLMs (built on LLaMA) for image and… | 33 | 2539 | active |
| VITA-MLLM/VITA VITA is an open-source interactive omni multimodal large language model (VITA-1.5) that supports real-time vision and speech interaction, s… | 26 | 2536 | active |