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 |
|---|---|---|---|
| PaddlePaddle/PaddleGAN PaddleGAN is a Python library providing high-performance implementations of classic and state-of-the-art Generative Adversarial Networks bu… | 23 | 8048 | maintenance |
| riddleling/iOS-OCR-Server An iOS app that turns an iPhone into a local OCR server using Apple's Vision Framework, exposing an HTTP API and web interface for image te… | 68 | 2085 | active |
| OpenSeeFace OpenSeeFace is a robust realtime face and facial landmark tracking library that runs on CPU at 30-60 fps using ONNX-converted MobileNetV3 m… | 85 | 2084 | active |
| alex-damian/pulse PULSE is a Python research implementation of a CVPR 2020 paper that upscales low-resolution face photos by searching the latent space of a … | 32 | 8026 | maintenance |
| alganzory/HaramBlur HaramBlur is a browser extension that automatically detects and blurs inappropriate images and videos on web pages using on-device machine … | 19 | 2083 | active |
| marcoslucianops/DeepStream-Yolo A collection of configuration files, parsers, and conversion utilities for running YOLO-family object detection models on NVIDIA DeepStream… | 57 | 2074 | active |
| facebookresearch/ConvNeXt-V2 Official PyTorch implementation of ConvNeXt V2, a family of pure convolutional neural network models co-designed with a fully convolutional… | 10 | 2065 | stable |
| facebookresearch/theseus Theseus is a PyTorch-based library for building custom differentiable nonlinear optimization layers, supporting problems in robotics and vi… | 23 | 2060 | active |
| zju3dv/GVHMR GVHMR is a research codebase implementing the SIGGRAPH Asia 2024 paper 'World-Grounded Human Motion Recovery via Gravity-View Coordinates'.… | 66 | 2059 | active |
| jd-opensource/JoyAI-Echo JoyAI-Echo is a Python framework for long-horizon audio-visual generation, producing coherent multi-shot videos up to ~5 minutes with paire… | 57 | 2057 | active |
| shanglianlm0525/PyTorch-Networks A collection of PyTorch implementations of classic and modern CNN architectures, covering classification, detection, segmentation, face, an… | 49 | 2056 | active |
| serengil/retinaface RetinaFace is a Python library for deep learning based face detection, built on TensorFlow and derived from the insightface project's Retin… | 66 | 2042 | active |
| hgjazhgj/FGO-py A fully automatic, configuration-free, cross-platform Fate/Grand Order assistant that automates farming, event climbing, and weekly mission… | 66 | 2040 | active |
| zxing-cpp/zxing-cpp ZXing-C++ is an open-source, multi-format 1D/2D barcode image processing library written in pure C++20, ported from the Java ZXing library … | 94 | 2039 | active |
| Tencent-Hunyuan/HunyuanOCR HunyuanOCR-1.5 is a lightweight end-to-end OCR vision-language model from Tencent, with a unified inference environment, llama.cpp PC-side … | 60 | 2025 | active |
| NVlabs/SPADE Official PyTorch implementation of SPADE (GauGAN), a CVPR 2019 method for synthesizing photorealistic images from semantic segmentation map… | 32 | 7717 | maintenance |
| UniFace UniFace is a unified Python library for face analysis that bundles detection, recognition, landmark localization, face parsing, gaze estima… | 85 | 2012 | active |
| cambrian-mllm/cambrian Cambrian-1 is a fully open family of vision-centric multimodal large language models (MLLMs) from NYU's VISIONx group, with training and ev… | 43 | 2011 | active |
| hkchengrex/XMem XMem is a PyTorch model for semi-supervised video object segmentation that tracks objects through long videos using an Atkinson-Shiffrin-in… | 23 | 1994 | stable |
| facebookresearch/dino PyTorch implementation of DINO, a self-supervised learning method for training Vision Transformers, with pretrained model weights. It is th… | 10 | 7609 | maintenance |
| xingyizhou/CenterNet CenterNet is a PyTorch implementation of the 'Objects as Points' detector, which models objects as single center points detected via keypoi… | 32 | 7574 | maintenance |
| Netflix/void-model VOID (Video Object and Interaction Deletion) is a research model from Netflix that removes objects from videos along with the physical inte… | 51 | 1983 | active |
| patrikhuber/eos A lightweight, header-only 3D Morphable Face Model (3DMM) fitting library written in modern C++11/14, with Python bindings. It provides mod… | 28 | 1981 | active |
| pythonOCC pythonocc-core is a Python package providing 3D modeling and data exchange features based on the OpenCascade Technology (OCCT) CAD kernel. … | 87 | 1980 | active |
| showlab/Show-o Show-o is a research repository implementing a unified transformer model that combines autoregressive and discrete diffusion modeling for m… | 48 | 1978 | active |
| Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB An ultra-lightweight face detection model (~1MB FP32, ~300KB quantized) designed for edge computing devices, with slim and RFB variants tra… | 32 | 7548 | maintenance |
| adobe-research/custom-diffusion Custom Diffusion is a research codebase for efficiently fine-tuning text-to-image diffusion models like Stable Diffusion on a few example i… | 66 | 1977 | stable |
| jd-opensource/JoyAI-VL-Interaction JoyAI-VL-Interaction is an open 8B-scale vision-language interaction model with a complete deployable real-time streaming system, including… | 59 | 1970 | active |
| JIA-Lab-research/DreamOmni2 DreamOmni2 is the official PyTorch implementation of a CVPR 2026 Highlight model for multimodal instruction-based image editing and generat… | 48 | 1968 | active |
| zs1083339604/FaceWinUnlock-Tauri A Windows face-recognition unlock application built with Tauri, Vue 3, and OpenCV that injects a custom Credential Provider DLL into the Wi… | 82 | 1962 | active |
| NVlabs/RADIO Official PyTorch implementation of AM-RADIO and its successors (RADIOv2.5, C-RADIOv4), agglomerative vision foundation models distilled fro… | 61 | 1961 | active |
| open-mmlab/mmagic MMagic is OpenMMLab's toolbox for generative and multimodal AI image/video creation, built on PyTorch. It provides a large model zoo coveri… | 23 | 7469 | maintenance |
| SizheAn/PanoHead PanoHead is the official PyTorch implementation of a CVPR 2023 paper presenting a 3D-aware GAN that synthesizes geometry-aware, view-consis… | 30 | 1960 | active |
| Yuliang-Liu/Monkey Monkey is a large multi-modal model (LMM) research project from CVPR 2024 that improves image understanding via higher input resolution and… | 71 | 1956 | active |
| alibaba/EasyCV EasyCV is an all-in-one PyTorch-based computer vision toolkit from Alibaba covering self-supervised learning, vision transformers, and majo… | 28 | 1955 | active |
| LTH14/mar Official PyTorch implementation of MAR (Masked Autoregressive) image generation with DiffLoss, from the NeurIPS 2024 paper 'Autoregressive … | 51 | 1954 | stable |
| eriklindernoren/PyTorch-YOLOv3 A minimal PyTorch implementation of YOLOv3 supporting training, inference, and evaluation, with compatibility for YOLOv4 and YOLOv7 weights… | 32 | 7439 | maintenance |
| rlguy/Blender-FLIP-Fluids A Blender addon providing a high-quality FLIP-based liquid fluid simulation engine, developed since 2016 and tightly integrated into Blende… | 83 | 1953 | active |
| Fafa-DL/Awesome-Backbones A PyTorch-based framework that integrates many deep learning backbone models (CNNs and vision transformers like ResNet, EfficientNet, Swin … | 32 | 1953 | active |
| microsoft/Magma Magma is Microsoft Research's foundation model for multimodal AI agents, released as an 8B vision-language model that understands images an… | 50 | 1948 | active |
| NVIDIA-AI-Blueprints/video-search-and-summarization NVIDIA's GPU-accelerated AI Blueprint reference architecture for building video analytics agents that search, summarize, and reason over li… | 86 | 1938 | active |
| NVlabs/nvdiffrast Nvdiffrast is a PyTorch library from NVIDIA providing high-performance, GPU-accelerated primitive operations for rasterization-based differ… | 49 | 1922 | stable |
| OpenTalker/video-retalking VideoReTalking is a Python research system from SIGGRAPH Asia 2022 that edits real-world talking-head videos to match a given audio track, … | 23 | 7292 | maintenance |
| pymatting/pymatting PyMatting is a Python library for alpha matting that estimates an alpha matte from an input image and a hand-drawn trimap to extract foregr… | 84 | 1918 | active |
| ButzYung/SystemAnimatorOnline XR Animator is an AI-based full-body motion capture application that uses a single webcam with MediaPipe and TensorFlow.js to drive MMD/VRM… | 92 | 1912 | active |
| visual-layer/fastdup fastdup is a free Python tool for rapidly analyzing image and video datasets to surface duplicates, outliers, broken, dark, bright, blurry,… | 64 | 1911 | active |
| diffgram/diffgram Diffgram is a self-hosted AI datastore for managing schemas, BLOBs, and predictions, with built-in human supervision (data labeling), data … | 59 | 1911 | active |
| sicxu/Deep3DFaceRecon_pytorch A PyTorch implementation of Deep3DFaceReconstruction, a weakly-supervised CNN method for reconstructing 3D face geometry from a single imag… | 32 | 1911 | stable |
| InteractiveComputerGraphics/SPlisHSPlasH SPlisHSPlasH is an open-source C++ library for physically-based fluid simulation using the Smoothed Particle Hydrodynamics (SPH) method. It… | 95 | 1906 | active |
| showlab/ShowUI ShowUI is an open-source, lightweight 2B vision-language-action model for GUI agents and computer use, accepted at CVPR 2025. The repositor… | 54 | 1906 | active |
| laugh12321/TensorRT-YOLO A C++/Python deployment toolkit for running YOLO-family models (YOLOv3 through YOLO26) on NVIDIA GPUs using TensorRT, with custom plugins, … | 71 | 1893 | active |
| ocrs Ocrs is a Rust library and CLI tool for optical character recognition that extracts text from images such as scanned documents, photos, and… | 70 | 1891 | active |
| rdumasia303/deepseek_ocr_app A self-hosted OCR web application combining a React frontend with a FastAPI backend, powered by the DeepSeek-OCR model. It processes images… | 47 | 1888 | active |
| KlingAIResearch/ReCamMaster ReCamMaster is a reference implementation of a camera-controlled generative video rendering model that re-renders a single source video alo… | 41 | 1887 | active |
| NVIDIA-AI-IOT/Lidar_AI_Solution NVIDIA's collection of GPU-accelerated Lidar AI inference solutions for autonomous driving, including optimized implementations of PointPil… | 69 | 1885 | active |
| Chinese License Plate Detection & Recognition A PyTorch-based Chinese license plate detection and recognition system built on YOLOv5 for detection and CRNN for recognition. It supports … | 67 | 1883 | active |
| koide3/glim GLIM is a versatile and extensible point cloud-based 3D localization and mapping (SLAM) framework written in C++. It performs direct multi-… | 76 | 1881 | active |
| qqwweee/keras-yolo3 A Keras (TensorFlow backend) implementation of YOLOv3 for object detection, including Darknet weight conversion, image/video detection scri… | 32 | 7113 | maintenance |
| jingsongliujing/OnnxOCR A lightweight multilingual OCR library rebuilt from PaddleOCR models to run on ONNXRuntime, removing the PaddlePaddle dependency for fast i… | 68 | 1876 | active |
| OpenImagingLab/FlashVSR FlashVSR is a one-step diffusion-based streaming video super-resolution framework that runs at ~17 FPS for 768x1408 video on a single A100 … | 59 | 1876 | active |
| vt-vl-lab/3d-photo-inpainting A Python research codebase from a CVPR 2020 paper that converts a single RGB-D image into a 3D photo using layered depth inpainting. It hal… | 32 | 7093 | maintenance |
| Omni-Avatar/OmniAvatar OmniAvatar is an audio-driven full-body avatar video generation model built on Wan2.1 text-to-video diffusion models with LoRA-based audio … | 31 | 1862 | active |
| ConsistentlyInconsistentYT/Pixeltovoxelprojector A Python tool that projects the motion of pixels onto a voxel representation, converting 2D pixel movement into 3D voxel space. It is a pop… | 39 | 1860 | active |
| Zheng-Chong/CatVTON CatVTON is a lightweight diffusion model for virtual try-on that swaps clothing onto a person image using a concatenation-based architectur… | 37 | 1860 | active |
| mkazhdan/PoissonRecon An implementation of Poisson Surface Reconstruction for turning oriented point clouds into watertight 3D meshes, evolved into a general ada… | 55 | 1858 | stable |
| gaomingqi/Track-Anything Track-Anything is an interactive tool for video object tracking and segmentation built on Segment Anything, XMem, and E2FGVI. Users specify… | 52 | 7010 | maintenance |
| thygate/stable-diffusion-webui-depthmap-script An extension for AUTOMATIC1111's Stable Diffusion WebUI that generates high-resolution depth maps from images using models like Marigold, M… | 32 | 1855 | active |
| facebookresearch/MetaCLIP Meta's research code and models for Meta CLIP, a reimplementation and scaling recipe for CLIP-style contrastive vision-language models, inc… | 76 | 1854 | active |
| SerpentAI Framework Serpent.AI is a Python framework for building game agents—AIs and bots that learn to play any video game you own—turning games into machine… | 10 | 6989 | maintenance |
| NVlabs/stylegan3 Official PyTorch implementation of StyleGAN3 (Alias-Free GANs), a state-of-the-art generative adversarial network for high-fidelity image s… | 32 | 6945 | maintenance |
| clovaai/donut Donut is an OCR-free end-to-end Transformer model for visual document understanding tasks such as document classification and information e… | 23 | 6928 | maintenance |
| NVIDIA/pix2pixHD PyTorch implementation of pix2pixHD, a conditional GAN method for synthesizing and manipulating high-resolution (2048x1024) photorealistic … | 32 | 6925 | maintenance |
| ytongbai/LVM LVM is a large vision model trained with sequential next-token prediction over 'visual sentences', using no linguistic data. It builds on O… | 31 | 1836 | active |
| norlab-ulaval/libpointmatcher libpointmatcher is a modular C++ library implementing the Iterative Closest Point (ICP) algorithm for aligning 2D and 3D point clouds, with… | 64 | 1835 | active |
| Stability-AI/stable-fast-3d Stable Fast 3D (SF3D) is Stability AI's open-source model that reconstructs a textured, UV-unwrapped 3D mesh from a single input image in a… | 24 | 1834 | active |
| AlibabaResearch/AdvancedLiterateMachinery A collection of original OCR and document understanding models, algorithms, and benchmarks from Alibaba's Tongyi Lab, including models like… | 52 | 1833 | active |
| ZFTurbo/Weighted-Boxes-Fusion A Python library implementing several methods for ensembling bounding boxes from multiple object detection models, including Non-maximum Su… | 66 | 1831 | stable |
| timothybrooks/instruct-pix2pix PyTorch implementation of InstructPix2Pix, a diffusion-based model that edits images according to natural language instructions (e.g., 'tur… | 32 | 6885 | maintenance |
| nvidia-isaac/cuVSLAM cuVSLAM is NVIDIA's CUDA-accelerated library for real-time visual odometry and simultaneous localization and mapping (SLAM). It supports mu… | 78 | 1824 | active |
| artivis/manif manif is a header-only C++11 library for Lie theory with Python 3 wrappers, providing common Lie groups (SO(2), SE(2), SO(3), SE(3), SE_2(3… | 62 | 1821 | active |
| potamides/DeTikZify DeTikZify is a Python library and research tool that uses multimodal large language models to synthesize TikZ/LaTeX graphics programs from … | 63 | 1819 | active |
| VAST-AI-Research/TripoSG TripoSG is an open-source image-to-3D generation foundation model that produces high-fidelity 3D meshes from single images using large-scal… | 24 | 1815 | active |
| zju3dv/4K4D 4K4D is a research implementation of a 4D point cloud representation for real-time dynamic view synthesis at up to 4K resolution, built on … | 70 | 1814 | active |
| apple/ml-4m 4M is a framework from Apple and EPFL for training any-to-any multimodal foundation models using masked modeling over discrete tokens acros… | 68 | 1814 | active |
| triple-mu/YOLOv8-TensorRT A library for running YOLOv8 inference accelerated with NVIDIA TensorRT, supporting detection, segmentation, pose estimation, oriented boun… | 72 | 1812 | active |
| allenai/ai2thor AI2-THOR is an open-source platform from the Allen Institute for AI providing near photo-realistic, interactable 3D environments (iTHOR, Ma… | 42 | 1809 | active |
| yerfor/GeneFacePlusPlus GeneFace++ is the official PyTorch implementation of a NeRF-based system for generalized and stable real-time 3D talking face generation. I… | 26 | 1808 | active |
| HuangJunJie2017/BEVDet BEVDet is a Python research codebase implementing the BEVDet series of bird's-eye-view (BEV) 3D object detection models for autonomous driv… | 23 | 1805 | active |
| zai-org/CogVLM CogVLM is an open-source visual language model (17B) combining a vision encoder with a pretrained language model for image understanding an… | 28 | 6745 | maintenance |
| QwenLM/Qwen-VL Official repository for Qwen-VL, Alibaba Cloud's large vision-language model family, including the pretrained Qwen-VL and instruction-tuned… | 29 | 6725 | maintenance |
| VAST-AI-Research/UniRig UniRig is the official implementation of a SIGGRAPH 2025 framework that automatically rigs 3D models by predicting skeletons and skinning w… | 55 | 1783 | active |
| Emu Series Emu3 is a suite of state-of-the-art multimodal models from BAAI trained solely with next-token prediction, tokenizing images, text, and vid… | 53 | 1777 | active |
| Totoro97/NeuS Official PyTorch implementation of NeuS, a neural implicit surface reconstruction method that learns SDF-based surfaces via volume renderin… | 32 | 1775 | stable |
| ianzhao/textshot TextShot is a Python command-line tool that lets you draw a rectangle over any screen region and copies the recognized text to your clipboa… | 32 | 1775 | active |
| puffinsoft/jscanify jscanify is an open-source pure JavaScript document scanning library powered by OpenCV.js. It detects and highlights documents in images an… | 70 | 1772 | active |
| ankitdhall/lidar_camera_calibration A ROS package that computes the rigid-body transformation (rotation and translation) between a LiDAR and a camera using 3D-3D point corresp… | 40 | 1771 | active |
| GAP-LAB-CUHK-SZ/gaustudio GauStudio is a modular PyTorch framework for 3D Gaussian Splatting (3DGS) research and development, supporting novel view synthesis, 3D rec… | 46 | 1763 | active |
| xinntao/ESRGAN ESRGAN (Enhanced SRGAN) is a PyTorch-based image super-resolution model that won the PIRM 2018 Challenge on Perceptual Super-Resolution. Th… | 32 | 6571 | maintenance |
| nguyenq/tess4j Tess4J is a Java JNA wrapper for the Tesseract OCR API, enabling optical character recognition in Java applications. It supports TIFF, JPEG… | 85 | 1757 | stable |
| kijai/ComfyUI-Florence2 A ComfyUI custom node plugin that runs Microsoft's Florence-2 vision-language model for image captioning, object detection, segmentation, a… | 57 | 1756 | active |