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 |
|---|---|---|---|
| open-mmlab/mmcv MMCV is the foundational computer vision library for the OpenMMLab ecosystem, providing image/video I/O, data transformations, and CUDA ope… | 48 | 6475 | stable |
| ByteDance-Seed/Depth-Anything-3 Depth Anything 3 (DA3) is a transformer-based model that predicts spatially consistent depth and geometry from any number of visual inputs,… | 56 | 6445 | active |
| madmaze/pytesseract Python-tesseract is a Python wrapper for Google's Tesseract-OCR engine that recognizes and extracts text embedded in images. It supports al… | 68 | 6396 | stable |
| mayocream/koharu Koharu is a local-first desktop application that automates manga translation using machine learning, combining text/bubble detection, OCR, … | 82 | 6394 | active |
| docTR docTR is a Python OCR library that extracts text from documents and images using a two-stage deep learning approach: text detection followe… | 86 | 6359 | active |
| KevinMusgrave/pytorch-metric-learning A PyTorch library providing modular losses, miners, samplers, and testers for deep metric learning. It supports building complete train/tes… | 43 | 6342 | active |
| szad670401/HyperLPR HyperLPR3 is a high-performance open-source framework for recognizing Chinese license plates, built with deep learning and available as a P… | 23 | 6270 | active |
| RangiLyu/nanodet NanoDet-Plus is a super fast, lightweight anchor-free object detection model implemented in PyTorch, with model sizes as small as 980KB (IN… | 23 | 6269 | stable |
| PaddlePaddle/PaddleX PaddleX is a low-code, all-in-one AI development tool built on the PaddlePaddle framework, bundling 200+ pretrained models into 33 producti… | 86 | 6268 | active |
| open-edge-platform/anomalib Anomalib is a Python deep learning library for anomaly detection, offering state-of-the-art unsupervised algorithms for detecting and local… | 96 | 6196 | active |
| ladaapp/lada Lada is an open-source tool with both GUI and CLI that restores pixelated/mosaic regions in videos, primarily targeting JAV (Japanese adult… | 59 | 6193 | active |
| ByteDance-Seed/Bagel BAGEL is an open-source unified multimodal foundation model with 7B active parameters (14B total) trained on interleaved multimodal data. I… | 52 | 6191 | active |
| bytedance/LatentSync LatentSync is an end-to-end lip-sync framework from ByteDance based on audio-conditioned latent diffusion models, using Stable Diffusion to… | 30 | 6120 | active |
| OpenCvSharp OpenCvSharp is a cross-platform .NET wrapper for the OpenCV computer vision library, published as NuGet packages with bundled native binari… | 100 | 6113 | active |
| CGAL/cgal CGAL (Computational Geometry Algorithms Library) is a mature C++ library providing efficient and reliable algorithms for computational geom… | 97 | 6071 | stable |
| Doubiiu/ToonCrafter ToonCrafter is a generative model that interpolates two cartoon images into a short animation by leveraging pre-trained image-to-video diff… | 26 | 6033 | stable |
| om-ai-lab/VLM-R1 VLM-R1 is a framework for training R1-style large vision-language models using reinforcement learning (GRPO) on top of Qwen2.5-VL. It provi… | 60 | 6029 | active |
| OFA-Sys/Chinese-CLIP Chinese-CLIP is a Chinese version of the CLIP model trained on ~200 million Chinese image-text pairs, built on open_clip. It provides APIs,… | 62 | 6014 | active |
| journeyapps/zxing-android-embedded An Android barcode scanning library built on the ZXing decoder, usable via Intents or embedded in an Activity for custom UI. It supports po… | 23 | 5936 | stable |
| ChaoningZhang/MobileSAM MobileSAM is the official implementation of a lightweight version of Meta's Segment Anything Model (SAM), replacing the heavyweight image e… | 62 | 5885 | stable |
| MeshLab MeshLab is an open source, portable, and extensible system for processing and editing unstructured large 3D triangular meshes, built on the… | 64 | 5858 | active |
| PaddlePaddle/PaddleClas PaddleClas is a Python library and toolkit for image classification, recognition, and retrieval built on the PaddlePaddle deep learning fra… | 66 | 5847 | active |
| DeepLabCut DeepLabCut is an open-source Python toolbox for markerless 2D and 3D pose estimation of user-defined body parts using deep neural networks … | 94 | 5784 | stable |
| NVIDIA/DALI NVIDIA DALI is a GPU-accelerated data loading and preprocessing library with optimized building blocks and an execution engine for deep lea… | 91 | 5761 | active |
| pjreddie/darknet Darknet is an open-source neural network framework written in C and CUDA, best known as the original home of the YOLO real-time object dete… | 32 | 26503 | maintenance |
| apple/ml-depth-pro Depth Pro is Apple's reference implementation of a foundation model for zero-shot metric monocular depth estimation, producing sharp high-r… | 66 | 5737 | active |
| open-mmlab/OpenPCDet OpenPCDet is a PyTorch-based open-source toolbox for LiDAR-based 3D object detection. It provides official implementations of models like P… | 49 | 5718 | active |
| nerfstudio gsplat is an open-source Python library with CUDA-accelerated, differentiable rasterization of Gaussians, based on 3D Gaussian Splatting fo… | 73 | 5716 | active |
| Fanghua-Yu/SUPIR SUPIR is a Python-based photo-realistic image restoration system built on SDXL diffusion priors and LLaVA captioning, presented at CVPR 202… | 33 | 5685 | active |
| idealo/imagededup imagededup is a Python library for finding exact and near-duplicate images in a collection using perceptual hashing algorithms (PHash, DHas… | 43 | 5678 | stable |
| lyuwenyu/RT-DETR Official implementation of RT-DETR and RT-DETRv2, real-time object detection transformers that outperform YOLO models, in PyTorch and Paddl… | 75 | 5609 | active |
| MiniGPT-4 Official code for MiniGPT-4 and MiniGPT-v2, vision-language models that align a frozen visual encoder with a frozen LLM (Vicuna) via a sing… | 30 | 25605 | maintenance |
| matterport/Mask_RCNN A Python implementation of the Mask R-CNN model for object detection and instance segmentation, built on Keras and TensorFlow with a ResNet… | 23 | 25573 | maintenance |
| ngxson/smolvlm-realtime-webcam A browser-based demo that streams webcam frames to a llama.cpp server running SmolVLM 500M for real-time object detection and scene descrip… | 26 | 5577 | active |
| obss/sahi SAHI (Slicing Aided Hyper Inference) is a Python vision library for detecting small objects in large images via sliced/tiled inference, wor… | 94 | 5513 | active |
| BIT-DataLab/Edit-Banana Edit Banana is an open-source Python framework that converts static images and PDFs of diagrams, flowcharts, and charts into fully editable… | 59 | 5498 | active |
| xxlong0/Wonder3D Wonder3D is a cross-domain diffusion model that reconstructs high-fidelity textured 3D meshes from a single image in 2-3 minutes. It genera… | 29 | 5437 | active |
| facebookresearch/sapiens Sapiens is a family of foundation models from Meta Reality Labs for human-centric vision tasks including 2D pose estimation, body-part segm… | 58 | 5432 | active |
| isl-org/MiDaS MiDaS is a Python library with pretrained models for robust monocular depth estimation from a single image, based on the TPAMI 2022 paper a… | 10 | 5419 | stable |
| roboflow/sports A Python library from Roboflow providing reusable computer vision tools for sports analytics, including ball tracking, player tracking and … | 72 | 5390 | active |
| deepseek-ai/DeepSeek-VL2 DeepSeek-VL2 is a series of Mixture-of-Experts vision-language models (Tiny, Small, and 4.5B activated parameters) with inference code and … | 22 | 5376 | active |
| Onmyoji Auto Script (OAS) OnmyojiAutoScript (OAS) is a free, open-source automation script for the mobile game Onmyoji, built on the AzurLaneAutoScript framework. It… | 64 | 5279 | active |
| Breakthrough/PySceneDetect PySceneDetect is a Python and OpenCV-based program and library for detecting scene cuts and transitions in videos, with multiple detection … | 95 | 5275 | stable |
| google-ar/arcore-android-sdk Google's ARCore SDK for Android, providing Java and C APIs for building augmented reality experiences with motion tracking, environmental u… | 90 | 5243 | active |
| katanaml/sparrow Sparrow is an open-source framework for structured data extraction from documents (PDFs, images) using ML, LLMs, and Vision LLMs, with sche… | 92 | 5225 | active |
| BallonsTranslator A desktop GUI application that uses deep learning to automatically translate comics and manga, combining text detection, OCR, inpainting, a… | 98 | 5206 | active |
| yisol/IDM-VTON Official implementation of IDM-VTON, an ECCV 2024 paper that improves diffusion models for high-fidelity virtual try-on, swapping garments … | 27 | 5206 | active |
| NVIDIAGameWorks/kaolin Kaolin is NVIDIA's PyTorch library of GPU-optimized modules for 3D deep learning research, covering meshes, point clouds, and 3D Gaussian s… | 66 | 5175 | active |
| timesler/facenet-pytorch A PyTorch library providing pretrained face detection (MTCNN) and facial recognition (Inception ResNet V1) models, ported from the TensorFl… | 38 | 5169 | stable |
| open-mmlab/mmaction2 MMAction2 is OpenMMLab's PyTorch-based toolbox and benchmark for video understanding, covering action recognition, temporal action localiza… | 52 | 5163 | active |
| facebookresearch/co-tracker CoTracker is a transformer-based model from Meta AI and Oxford VGG that jointly tracks any point (pixel) across a video, handling occlusion… | 57 | 5149 | active |
| ArthurBrussee/brush Brush is a 3D reconstruction engine using Gaussian splatting, built in Rust on the Burn ML framework and WebGPU. It trains and renders spla… | 64 | 5148 | active |
| opentrack/opentrack opentrack is a head tracking application that captures a user's head movements via webcams, IR trackers, or hardware devices and relays the… | 72 | 5145 | active |
| ai-dawang/PlugNPlay-Modules A curated collection of plug-and-play deep learning modules (convolutions, attention mechanisms, downsampling, and feature fusion blocks) i… | 35 | 5120 | active |
| libigl libigl is a simple C++ geometry processing library offering a wide range of algorithms for triangle and tetrahedral meshes, including defor… | 85 | 5105 | stable |
| facebookresearch/AugLy AugLy is a Python data augmentation library from Meta AI supporting audio, image, text, and video with over 100 augmentations. It focuses o… | 66 | 5097 | stable |
| manycore-research/SpatialLM SpatialLM is a 3D large language model that processes point cloud data (from monocular video, RGBD images, or LiDAR) and generates structur… | 59 | 5094 | active |
| Deci-AI/super-gradients SuperGradients is an open-source PyTorch-based training library for building, training, and fine-tuning state-of-the-art computer vision mo… | 50 | 5072 | active |
| MaaXYZ/MaaFramework MaaFramework is an automation black-box testing framework based on image recognition, rewritten from the experience of the MAA (MaaAssistan… | 94 | 5038 | active |
| KaiyangZhou/deep-person-reid Torchreid is a PyTorch library for deep-learning person re-identification, supporting both image and video reid with end-to-end training an… | 47 | 4926 | stable |
| zju3dv/EasyMocap EasyMocap is an open-source Python toolbox for markerless human motion capture and novel view synthesis from RGB videos. It fits parametric… | 66 | 4898 | active |
| tyxsspa/AnyText AnyText is the official implementation of a diffusion-based model for multilingual visual text generation and editing in images, accepted a… | 29 | 4883 | active |
| f3d-app/f3d F3D is a fast, minimalist open-source 3D viewer desktop application supporting many formats (glTF, USD, STL, STEP, OBJ, FBX, Alembic) with … | 85 | 4821 | active |
| cvg/LightGlue LightGlue is a deep neural network library that matches sparse local features across image pairs with high accuracy and fast inference. It … | 47 | 4820 | stable |
| UX-Decoder/Segment-Everything-Everywhere-All-At-Once SEEM is the official PyTorch implementation of the NeurIPS 2023 paper 'Segment Everything Everywhere All at Once', a model for universal im… | 21 | 4792 | stable |
| CloudCompare CloudCompare is a 3D point cloud and triangular mesh processing application, originally built to compare point clouds from laser scanners a… | 86 | 4788 | active |
| OpenDriveLab/UniAD UniAD is a unified end-to-end autonomous driving framework that hierarchically casts perception, prediction, and planning tasks under a pla… | 41 | 4766 | active |
| facebookresearch/vjepa2 Official PyTorch codebase and pretrained models for V-JEPA 2, a self-supervised video encoder trained on internet-scale video, plus V-JEPA … | 49 | 4758 | active |
| hku-mars/FAST-LIVO2 FAST-LIVO2 is a fast, tightly-coupled LiDAR-inertial-visual odometry and mapping system written in C++ on ROS. It provides real-time, accur… | 54 | 4755 | active |
| open-mmlab/mmocr MMOCR is OpenMMLab's PyTorch-based toolbox for text detection, recognition, and key information extraction. It provides a model zoo of OCR … | 23 | 4752 | active |
| esimov/pigo Pigo is a pure Go library for fast face detection, pupil/eye localization, and facial landmark detection based on the Pixel Intensity Compa… | 28 | 4741 | stable |
| Tencent/TNN TNN is a high-performance, lightweight deep learning inference framework developed by Tencent Youtu Lab, supporting mobile, desktop, and se… | 28 | 4656 | active |
| facebookresearch/vggt-omega VGGT-Omega is a research library from Oxford VGG and Meta AI providing pretrained transformer models for 3D vision tasks such as camera pos… | 58 | 4644 | active |
| joanrod/star-vector StarVector is a foundation model that generates scalable vector graphics (SVG) code from images and text by treating vectorization as a cod… | 46 | 4629 | active |
| NVlabs/neuralangelo Official PyTorch implementation of Neuralangelo, a CVPR 2023 method for high-fidelity neural surface reconstruction from multi-view images.… | 29 | 4615 | active |
| royshil/obs-backgroundremoval An OBS Studio plugin that removes and replaces the background in portrait video using ONNX-based machine learning segmentation, acting as a… | 95 | 4607 | active |
| sensity-ai/dot dot (Deepfake Offensive Toolkit) is a Python tool that generates real-time, controllable deepfakes from a webcam feed and injects them into… | 23 | 4589 | active |
| ceres-solver/ceres-solver Ceres Solver is an open-source C++ library for modeling and solving large-scale non-linear optimization problems, including bounded non-lin… | 77 | 4581 | stable |
| TencentARC/InstantMesh InstantMesh is a feed-forward framework for generating 3D meshes from a single image using sparse-view large reconstruction models (LRM/Ins… | 25 | 4545 | active |
| rom1504/img2dataset A Python tool that downloads large sets of image URLs and packages them into machine learning datasets, with resizing and caption support. … | 52 | 4454 | active |
| EvolvingLMMs-Lab/lmms-eval lmms-eval is a unified Python framework for evaluating large multimodal models across text, image, video, and audio tasks, with 100+ benchm… | 87 | 4453 | active |
| layumi/Person_reID_baseline_pytorch A small, friendly PyTorch baseline implementation for person and vehicle re-identification (ReID). It reproduces strong top-conference resu… | 67 | 4450 | stable |
| xlite-dev/lite.ai.toolkit A lightweight C++ toolkit providing unified APIs for 100+ pre-trained AI models across inference backends like ONNX Runtime, MNN, TensorRT,… | 72 | 4439 | active |
| huawei-noah/Efficient-AI-Backbones A collection of efficient neural network backbone architectures (GhostNet, TNT, ViG, WaveMLP, TinyNet, etc.) from Huawei Noah's Ark Lab, wi… | 24 | 4423 | active |
| Pot App Pot is a cross‑platform desktop application for instant text translation, OCR, and speech synthesis. It runs on Windows, macOS and Linux us… | 10 | 19418 | maintenance |
| open-compass/VLMEvalKit VLMEvalKit is an open-source Python toolkit for evaluating large vision-language models (LMMs/LVLMs) across 80+ benchmarks with support for… | 61 | 4412 | active |
| dreamgaussian/dreamgaussian DreamGaussian is the official PyTorch implementation of an ICLR 2024 Oral paper for efficient 3D content creation using generative Gaussian… | 19 | 4360 | active |
| VectorSpaceLab/OmniGen OmniGen is a unified diffusion-based image generation model that produces and edits images from multi-modal prompts without auxiliary modul… | 44 | 4346 | active |
| unum-cloud/USearch USearch is a fast, single-file similarity search and clustering engine for vectors and arbitrary objects, supporting spatial, binary, proba… | 89 | 4325 | active |
| richzhang/PerceptualSimilarity A PyTorch library implementing the LPIPS (Learned Perceptual Image Patch Similarity) metric, which measures perceptual distance between ima… | 23 | 4280 | stable |
| SysCV/sam-hq HQ-SAM (Segment Anything in High Quality) upgrades Meta's Segment Anything Model with a learnable High-Quality Output Token for accurate ze… | 45 | 4262 | active |
| ZhengPeng7/BiRefNet BiRefNet is a PyTorch implementation of the CAAI AIR 2024 paper 'Bilateral Reference for High-Resolution Dichotomous Image Segmentation'. I… | 64 | 4247 | active |
| ali-vilab/AnyDoor AnyDoor is the official implementation of a diffusion-based model that teleports target objects into new scenes at user-specified locations… | 29 | 4241 | active |
| cvg/Hierarchical-Localization hloc is a modular Python toolbox for state-of-the-art 6-DoF visual localization, combining image retrieval and feature matching (SuperPoint… | 44 | 4232 | active |
| solvespace/solvespace SolveSpace is a free, open-source parametric 2D/3D CAD application with a constraint-based sketcher and solid modeling via extrudes, revolv… | 78 | 4204 | active |
| WebODM/WebODM WebODM is a user-friendly, commercial-grade application for drone image processing that generates georeferenced maps, point clouds, elevati… | 96 | 4199 | active |
| torchgeo/torchgeo TorchGeo is a PyTorch domain library, similar to torchvision, providing datasets, samplers, transforms, and pre-trained models specific to … | 93 | 4192 | active |
| JEPA Official PyTorch implementation of V-JEPA, a self-supervised method for learning visual representations from video using a joint-embedding … | 26 | 4179 | active |
| shitagaki-lab/see-through A research framework from a SIGGRAPH 2026 paper that decomposes a single anime character illustration into up to 23 fully inpainted, semant… | 58 | 4153 | active |
| OpenMVS OpenMVS is an open-source C++ library for Multi-View Stereo 3D reconstruction, taking camera poses and a sparse point-cloud as input and pr… | 74 | 4149 | active |