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 |
|---|---|---|---|
| rpautrat/SuperPoint A TensorFlow (with PyTorch conversion) implementation of the SuperPoint self-supervised interest point detector and descriptor network. It … | 37 | 2528 | stable |
| FacePlugin Face Recognition SDK An open-source face recognition SDK by Faceplugin providing face detection, landmark extraction, feature embedding generation, and face tem… | 65 | 2526 | active |
| luanfujun/deep-photo-styletransfer Reference implementation of the CVPR 2017 paper 'Deep Photo Style Transfer', performing photorealistic image style transfer using Torch wit… | 32 | 9982 | maintenance |
| Epic Awesome Gamer A Python library that solves hCaptcha challenges using multimodal large language models and ONNX vision models (YOLO, CLIP, ResNet) integra… | 80 | 2508 | active |
| yformer/EfficientSAM EfficientSAM is an efficient image segmentation model that leverages masked image pretraining to provide a lightweight alternative to Meta'… | 27 | 2498 | active |
| AngusJohnson/Clipper2 Clipper2 is a polygon clipping, offsetting, and triangulation library available in C++, C#, and Delphi. It performs boolean operations (int… | 70 | 2496 | active |
| twistedfall/opencv-rust Rust bindings for the OpenCV computer vision library, generated automatically via Clang. It exposes OpenCV 3.4 (deprecated), 4.x, and 5.x A… | 75 | 2494 | active |
| sthalles/SimCLR A PyTorch reference implementation of SimCLR, a self-supervised contrastive learning framework for learning visual representations from unl… | 23 | 2494 | stable |
| ipazc/mtcnn A Python library implementing the MTCNN (Multitask Cascaded Convolutional Networks) algorithm for face detection and facial landmark alignm… | 23 | 2490 | stable |
| GaParmar/img2img-turbo A research library implementing one-step image-to-image translation models (CycleGAN-Turbo and pix2pix-turbo) built on SD-Turbo diffusion m… | 38 | 2488 | active |
| ppogg/YOLOv5-Lite YOLOv5-Lite is a lightweight object detection model family evolved from YOLOv5, with models as small as ~900KB (int8) that run 10-15+ FPS o… | 23 | 2488 | active |
| jyjblrd/Low-Cost-Mocap A low-cost, room-scale motion capture system built with PlayStation cameras and ESP32 hardware, used to track objects and autonomously fly … | 29 | 2487 | active |
| xuebinqin/U-2-Net Official PyTorch implementation of U^2-Net, a nested U-structure deep network for salient object detection, published in Pattern Recognitio… | 32 | 9875 | maintenance |
| wgsxm/PartCrafter PartCrafter is a structured 3D generative model that jointly generates multiple semantically meaningful 3D mesh parts and objects from a si… | 50 | 2485 | active |
| homuler/MediaPipeUnityPlugin A Unity native plugin that ports the MediaPipe C++ API to C#, enabling MediaPipe graphs and solutions to run inside Unity applications. It … | 56 | 2484 | active |
| roboflow/inference Roboflow Inference is a Python library and self-hostable inference server for deploying computer vision models on any computer or edge devi… | 91 | 2474 | active |
| hku-mars/r3live R3LIVE is a tightly-coupled LiDAR-Inertial-Visual sensor fusion framework for robust, real-time state estimation and RGB-colored 3D mapping… | 44 | 2473 | active |
| Alibaba-Quark/LiveAvatar LiveAvatar is an open-source implementation of an ECCV 2026 paper for streaming, real-time, infinite-length audio-driven avatar video gener… | 58 | 2456 | active |
| kevmo314/magic-copy Magic Copy is a browser extension (Chrome, Firefox, and Figma) that uses Meta's Segment Anything Model to segment a foreground object from … | 21 | 2454 | active |
| facebookresearch/pifuhd PIFuHD is a PyTorch implementation of a CVPR 2020 research model that reconstructs high-resolution 3D human body meshes from a single 2D im… | 10 | 9724 | maintenance |
| nv-tlabs/3dgrut NVIDIA's official implementations of 3D Gaussian Ray Tracing (3DGRT) and 3D Gaussian Unscented Transform (3DGUT), which render volumetric G… | 68 | 2441 | active |
| schappim/macOCR macOCR is a macOS command-line tool that captures a screen region you select and runs OCR on it, copying the recognized text (or QR/barcode… | 90 | 2438 | active |
| wangshub/Douyin-Bot A Python bot that automates the Douyin (TikTok China) mobile app via ADB, taking screenshots and calling a face-recognition API to auto-lik… | 32 | 9644 | maintenance |
| pixpark/gpupixel GPUPixel is a high-performance, cross-platform real-time image and video filter library written in C++11 and built on OpenGL/ES. It provide… | 84 | 2430 | active |
| wolny/pytorch-3dunet A PyTorch implementation of 3D U-Net and its variants (residual, squeeze-and-excitation) for volumetric semantic segmentation, with 2D U-Ne… | 57 | 2423 | active |
| HuCaoFighting/Swin-Unet Official PyTorch implementation of Swin-Unet, a U-shaped pure Transformer model for medical image segmentation, published at ECCV 2022 Medi… | 38 | 2420 | stable |
| Smorodov/Multitarget-tracker A C++ library for multiple object tracking that combines detectors (YOLO, D-FINE, RF-DETR, MobileNet-SSD) with tracking algorithms based on… | 67 | 2418 | active |
| X-PLUG/mPLUG-DocOwl mPLUG-DocOwl is a family of multimodal large language models from Alibaba for OCR-free document understanding, including DocOwl1.5 and DocO… | 37 | 2413 | active |
| ailia models A collection of 400+ pre-trained state-of-the-art AI models (object detection, pose estimation, speech recognition, LLMs, image generation,… | 76 | 2393 | active |
| OpenGVLab/InternVideo InternVideo is a series of open-source video foundation models for multimodal video understanding, spanning generative and discriminative l… | 69 | 2393 | active |
| zai-org/GLM-V GLM-V is the open-source repository for Zhipu AI's GLM-4.6V, GLM-4.5V, and GLM-4.1V-Thinking vision-language models, which perform versatil… | 63 | 2393 | active |
| Cicada000/VV A Python application that indexes video clips of a public figure (mainly from the TV show 'This Is China') by combining face recognition (d… | 32 | 2387 | active |
| TencentARC/Pixal3D Pixal3D is a research codebase for generating high-fidelity 3D assets from a single image using a pixel-aligned generation paradigm that ba… | 56 | 2383 | active |
| facebookresearch/perception_models Meta's Perception Models repository hosting state-of-the-art image, video, and audio encoders (Perception Encoder, PE) and a multimodal lan… | 51 | 2382 | active |
| MouseLand/cellpose Cellpose is a generalist deep learning algorithm for cellular and nucleus segmentation in microscopy images, with human-in-the-loop capabil… | 80 | 2371 | active |
| Tongyi-MAI/MAI-UI Qwen-UI-Agent (MAI-UI) is a foundation GUI agent model from Alibaba's Tongyi-MAI team that unifies mobile, desktop, browser, and deep-resea… | 57 | 2369 | active |
| tencent-ailab/V-Express V-Express is a Python research project from Tencent AI Lab that generates talking head portrait videos from a reference image, audio, and V… | 25 | 2357 | active |
| elalish/manifold A C++ geometry library for creating and operating on manifold triangle meshes that represent solid objects, with guaranteed topologically r… | 98 | 2355 | stable |
| MIT-SPARK/TEASER-plusplus TEASER++ is a fast and certifiably-robust C++ library for rigid body point cloud registration in 3D, with Python and MATLAB bindings. It es… | 44 | 2346 | stable |
| NextLevel/NextLevel NextLevel is a Swift camera capture library for iOS built on AVFoundation, providing photo and video capture, multi-clip recording, ARKit i… | 67 | 2331 | active |
| YvanYin/Metric3D Metric3D is the official PyTorch implementation of Metric3Dv1 and Metric3Dv2, monocular geometric foundation models that predict metric dep… | 31 | 2326 | active |
| PKU-YuanGroup/MoE-LLaVA MoE-LLaVA is an open-source Mixture-of-Experts based sparse large vision-language model, released with the MoE-Tuning training strategy fro… | 28 | 2324 | active |
| UZ-SLAMLab/ORB_SLAM3 ORB-SLAM3 is a real-time SLAM library supporting Visual, Visual-Inertial, and Multi-Map SLAM with monocular, stereo, and RGB-D cameras usin… | 23 | 9125 | maintenance |
| Cadene/pretrained-models.pytorch A Python library providing pretrained ConvNet models (ResNet, ResNeXt, InceptionV4, Xception, NASNet, SENet, DPN, etc.) for PyTorch behind … | 32 | 9101 | maintenance |
| nv-tlabs/lyra Project Lyra is NVIDIA's open series of generative 3D world models, including Lyra 1.0 for feed-forward 3D/4D scene generation from a singl… | 56 | 2317 | active |
| gruhn/vue-qrcode-reader A set of Vue.js 3 components for detecting and decoding QR codes and other barcode formats directly in the browser. It provides QrcodeStrea… | 72 | 2314 | active |
| IDEA-Research/detrex detrex is an open-source PyTorch-based research platform and toolbox for DETR-style Transformer detection algorithms, built on top of Detec… | 38 | 2311 | active |
| frgfm/torch-cam TorchCAM is a Python library that extracts class activation maps (CAMs) from PyTorch CNN classifiers, supporting many CAM variants such as … | 88 | 2307 | active |
| emgucv/emgucv Emgu CV is a cross-platform .NET wrapper for the OpenCV image processing library, allowing OpenCV functions to be called from .NET-compatib… | 90 | 2300 | active |
| traveller59/spconv SpConv is a spatially sparse convolution library for deep learning on 3D point clouds and sparse tensors, distributed as PyPI packages with… | 32 | 2299 | active |
| NVlabs/nvdiffrec nvdiffrec is NVIDIA's official implementation of a CVPR 2022 oral paper that jointly optimizes triangular 3D meshes, PBR materials, and lig… | 72 | 2298 | stable |
| THU-MIG/yoloe YOLOE is the official PyTorch implementation of an open-vocabulary object detection and segmentation model presented at ICCV 2025. It unifi… | 30 | 2297 | active |
| andrewssobral/bgslibrary BGSLibrary is a C++ framework for background subtraction in video, offering 43 algorithms for foreground-background separation built on Ope… | 57 | 2282 | active |
| Liuziyu77/Visual-RFT Official research code for Visual-RFT and Visual-ARFT, applying GRPO-based reinforcement fine-tuning with rule-based verifiable rewards to … | 39 | 2280 | active |
| opendatalab/DocLayout-YOLO DocLayout-YOLO is a real-time YOLO-v10-based model for detecting document layout elements (text blocks, tables, figures, etc.) in diverse d… | 26 | 2277 | active |
| OlafenwaMoses/ImageAI ImageAI is a Python library that lets developers add computer vision capabilities like image classification, object detection, and video ob… | 23 | 8888 | maintenance |
| ermig1979/Simd Simd Library is a free open-source C++ image processing and machine learning library with a C API and Python wrapper. Its algorithms are ha… | 98 | 2272 | active |
| ashawkey/stable-dreamfusion A PyTorch implementation of Dreamfusion that generates 3D models from text prompts or images using NeRF combined with Stable Diffusion guid… | 23 | 8865 | maintenance |
| stepfun-ai/Step1X-Edit Step1X-Edit is an open-source state-of-the-art instruction-based image editing model from StepFun, designed to rival closed-source editors … | 52 | 2266 | active |
| yemount/pose-animator Pose Animator is a browser-based tool that animates 2D SVG vector characters in real time using pose and face keypoints detected by PoseNet… | 32 | 8851 | maintenance |
| facebookresearch/fvcore fvcore is a lightweight Python core library providing common functionality shared across FAIR's computer vision frameworks such as Detectro… | 73 | 2254 | stable |
| CoinCheung/pytorch-loss A PyTorch library providing a collection of loss functions (focal loss, triplet loss, AMSoftmax, label-smooth CE, dice loss, lovasz-softmax… | 32 | 2251 | active |
| DepthAnything/Video-Depth-Anything Video Depth Anything is a transformer-based monocular depth estimation model for arbitrarily long videos, built on Depth Anything V2. It pr… | 35 | 2247 | active |
| Raster Vision Raster Vision is an open source Python library and low-code framework for building computer vision models on satellite, aerial, and other l… | 57 | 2241 | active |
| NVlabs/MambaVision MambaVision is NVIDIA's official PyTorch implementation of a hybrid Mamba-Transformer vision backbone, published at CVPR 2025. It provides … | 46 | 2235 | active |
| NVIDIA/vid2vid A PyTorch implementation of NVIDIA's video-to-video synthesis method for generating high-resolution (e.g., 2048x1024) photorealistic videos… | 32 | 8692 | maintenance |
| apple/ml-ferret Apple's Ferret, an end-to-end multimodal large language model (MLLM) that accepts any-form referring and grounds anything in its responses,… | 70 | 8655 | maintenance |
| unrealcv/unrealcv UnrealCV is an open-source Unreal Engine plugin that connects computer vision research to virtual worlds by exposing a command API and Pyth… | 94 | 2219 | active |
| google-deepmind/tapnet Google DeepMind's official repository for Tracking Any Point (TAP), containing the TAP-Vid and TAPVid-3D benchmarks, the TAPIR and TAPNext … | 75 | 2217 | active |
| kijai/ComfyUI-LivePortraitKJ ComfyUI custom nodes that integrate the LivePortrait face animation and retargeting model, supporting image-to-video, video-to-video, and n… | 24 | 2211 | active |
| MVIG-SJTU/AlphaPose AlphaPose is an open-source real-time multi-person full-body pose estimation and tracking system built on PyTorch. It detects human keypoin… | 32 | 8605 | maintenance |
| WebODM/OpenSplat OpenSplat is a free, open-source C++ implementation of 3D gaussian splatting that turns camera poses and sparse points into splat scene fil… | 91 | 2205 | active |
| kleinlee/DH_live DH_live (mini) is an open-source 2D talking-head digital human toolkit that generates real-time lip-synced avatar video from a single refer… | 64 | 2202 | active |
| spla-tam/SplaTAM SplaTAM is a dense RGB-D SLAM system that uses 3D Gaussian splatting for high-fidelity scene reconstruction and precise camera tracking fro… | 18 | 2200 | active |
| TimmyOVO/deepseek-ocr.rs A Rust implementation of the DeepSeek-OCR inference stack with multiple OCR/VLM backends (DeepSeek-OCR, PaddleOCR-VL, DotsOCR), DSQ quantiz… | 54 | 2189 | active |
| yyfz/Pi3 Pi3 (π³) is a feed-forward neural network for visual geometry reconstruction that eliminates the need for a fixed reference view, using a p… | 56 | 2188 | active |
| yatengLG/ISAT_with_segment_anything ISAT_with_segment_anything is an interactive semi-automatic image annotation tool built on the Segment Anything Model family (SAM, SAM2, SA… | 81 | 2186 | active |
| sirfz/tesserocr A Python wrapper around the tesseract-ocr C++ API built with Cython for optical character recognition. It is Pillow-friendly, works with im… | 86 | 2173 | active |
| ViTAE-Transformer/ViTPose Official PyTorch implementation of ViTPose and ViTPose++, Vision Transformer models for human and generic body pose estimation from NeurIPS… | 55 | 2173 | stable |
| Tencent-Hunyuan/HunyuanVideo-Avatar HunyuanVideo-Avatar is Tencent's open-source model and inference code for high-fidelity audio-driven human animation, generating talking av… | 42 | 2173 | active |
| muskie82/MonoGS MonoGS is a dense SLAM system that applies 3D Gaussian Splatting to monocular, stereo, and RGB-D camera tracking and mapping, presented at … | 26 | 2164 | active |
| 1038lab/ComfyUI-RMBG A ComfyUI custom node package for advanced image background removal and segmentation of objects, faces, clothing, and fashion elements. It … | 66 | 2162 | active |
| JasonMa0012/JTRP JTRP is a Unity HDRP-based toon shading (cel shading / NPR) render pipeline toolkit supporting DX12 ray tracing, built as a second developm… | 23 | 2161 | active |
| MRPT/mrpt MRPT is a mature C++ toolkit of libraries and applications for mobile robotics, covering SLAM, localization, probabilistic filtering, senso… | 94 | 2160 | stable |
| SpikingJelly SpikingJelly is an open-source deep learning framework for Spiking Neural Networks (SNNs) built on PyTorch. It provides a beginner-friendly… | 77 | 2159 | active |
| facebookresearch/mae A PyTorch/GPU re-implementation of the Masked Autoencoders (MAE) paper for self-supervised vision learning. It includes pre-training code, … | 10 | 8362 | maintenance |
| espressif/esp-who ESP-WHO is an image processing development platform from Espressif providing face detection, face recognition, pedestrian detection, and QR… | 63 | 2156 | active |
| jd-opensource/JoyAI-Image JoyAI-Image is a unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editin… | 54 | 2156 | active |
| baowenbo/DAIN DAIN is a PyTorch-based deep learning model for depth-aware video frame interpolation, synthesizing intermediate frames between existing on… | 32 | 8316 | maintenance |
| PKU-YuanGroup/LLaVA-CoT LLaVA-CoT is an 11B vision language model with training, inference, and dataset-generation code for spontaneous step-by-step multimodal rea… | 44 | 2131 | active |
| LiheYoung/Depth-Anything Depth Anything is a monocular depth estimation foundation model trained on 1.5M labeled and 62M+ unlabeled images, released as a Python lib… | 26 | 8240 | maintenance |
| utkuozbulak/pytorch-cnn-visualizations A PyTorch library implementing a wide range of convolutional neural network visualization and interpretability techniques, including Grad-C… | 32 | 8236 | maintenance |
| lukemelas/EfficientNet-PyTorch A PyTorch implementation of the EfficientNet convolutional neural network family with pretrained ImageNet weights. It provides a simple pip… | 23 | 8219 | maintenance |
| autonomousvision/sdfstudio SDFStudio is a unified and modular framework for neural implicit surface reconstruction built on top of nerfstudio. It provides unified imp… | 32 | 2124 | active |
| nv-tlabs/vipe ViPE is an open-source video processing engine from NVIDIA that estimates camera intrinsics, camera motion, and dense near-metric depth map… | 77 | 2122 | active |
| 3DTopia/LGM LGM is the official PyTorch implementation of an ECCV 2024 Oral paper that generates high-resolution 3D models from text prompts or single-… | 26 | 2118 | active |
| SUDO-AI-3D/zero123plus Zero123++ is a diffusion base model that generates consistent multi-view images from a single input image, intended as a stepping stone for… | 28 | 2099 | active |
| RenderKit/oidn Intel Open Image Denoise is an open-source library of high-performance, deep-learning-based denoising filters for images rendered with ray … | 88 | 2097 | stable |
| DanBloomberg/leptonica Leptonica is an open-source C library providing a broad set of image processing and image analysis operations, with a focus on document ima… | 74 | 2092 | stable |
| visomaster/VisoMaster VisoMaster is a Python-based desktop application for AI-powered face swapping and face editing in images and videos. It supports multiple s… | 24 | 2089 | active |