domain: computer-vision
2316 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| bytedeco/javacpp-presets JavaCPP Presets provides Java bindings for commonly used native C++ libraries such as OpenCV, FFmpeg, and many others, built on the JavaCPP… | 86 | 2850 | active |
| OpenGVLab/InternImage InternImage is a large-scale CNN-based vision foundation model that uses deformable convolutions as its core operator, released with pretra… | 28 | 2841 | stable |
| 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 | 11452 | maintenance |
| google-research/kubric Kubric is a data generation pipeline from Google Research for creating semi-realistic synthetic multi-object videos with rich annotations l… | 60 | 2808 | 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… | 66 | 2807 | 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… | 94 | 2800 | 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… | 66 | 2796 | stable |
| 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… | 57 | 2795 | 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… | 26 | 2780 | active |
| 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 | 2777 | active |
| gem5/gem5 gem5 is the official open-source computer-system architecture simulator for research and teaching, modeling processor microarchitecture and… | 88 | 2771 | active |
| autodistill/autodistill Autodistill is a Python library that uses large foundation vision models (like Grounding DINO, Grounded SAM, and CLIP) to automatically lab… | 29 | 2763 | active |
| NVlabs/stylegan2 The official TensorFlow implementation of StyleGAN2, NVIDIA's improved style-based generative adversarial network for high-quality uncondit… | 32 | 11184 | maintenance |
| NVIDIA/FastPhotoStyle FastPhotoStyle is NVIDIA's official PyTorch implementation of the ECCV 2018 paper 'A Closed-form Solution to Photorealistic Image Stylizati… | 23 | 11177 | 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… | 90 | 2758 | stable |
| apple/turicreate Turi Create is a Python library from Apple that simplifies building custom machine learning models for tasks like image classification, obj… | 10 | 11159 | maintenance |
| 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 | 2750 | 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 | 2750 | active |
| 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… | 99 | 2747 | active |
| stevenlovegrove/Pangolin Pangolin is a lightweight, portable C++ utility library for rapid prototyping of 3D, numeric, and video-based programs, providing cross-pla… | 87 | 2739 | stable |
| 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… | 93 | 2718 | active |
| 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 | 2718 | 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 | 10962 | maintenance |
| bmild/nerf The official TensorFlow implementation of NeRF (Neural Radiance Fields), the ECCV 2020 paper representing scenes as neural radiance fields … | 39 | 10927 | maintenance |
| 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… | 96 | 2705 | 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… | 19 | 2704 | stable |
| magic-research/magic-animate MagicAnimate is the official implementation of a CVPR 2024 diffusion-based human image animation framework that animates a reference image … | 44 | 10897 | maintenance |
| 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… | 28 | 2701 | active |
| 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… | 48 | 2699 | active |
| 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… | 68 | 2695 | active |
| roboflow/maestro maestro is a Python library from Roboflow that streamlines fine-tuning of multimodal vision-language models such as Florence-2, PaliGemma 2… | 62 | 2694 | 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 | 2691 | active |
| torinmb/mediapipe-touchdesigner A GPU-accelerated, self-contained MediaPipe plugin for TouchDesigner that runs MediaPipe vision models (face detection, face/hand/pose trac… | 86 | 2686 | active |
| bytedance/InfiniteYou InfiniteYou (InfU) is a research framework from ByteDance for identity-preserved text-to-image generation built on Diffusion Transformers l… | 37 | 2685 | active |
| MrGiovanni/UNetPlusPlus Official implementation of UNet++, a nested U-Net architecture for medical image segmentation, in both Keras and PyTorch. It redesigns skip… | 77 | 2679 | stable |
| HiLab-git/SSL4MIS A benchmark and code collection of semi-supervised learning methods for medical image segmentation, re-implementing approaches like Mean Te… | 44 | 2676 | 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… | 31 | 2676 | stable |
| JIA-Lab-research/LISA LISA (Large Language Instructed Segmentation Assistant) is a multimodal large language model that performs reasoning-based image segmentati… | 31 | 2674 | 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 … | 41 | 2671 | 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… | 94 | 2670 | stable |
| IceClear/StableSR StableSR is a Python research library that leverages pre-trained Stable Diffusion priors for real-world blind image super-resolution. It pr… | 21 | 2668 | stable |
| om-ai-lab/OmAgent OmAgent is a Python library for building multimodal language agents, wrapping worker orchestration, task queues, and graph-based workflow o… | 31 | 2665 | active |
| aigc3d/LHM LHM is a PyTorch-based large reconstruction model that reconstructs high-fidelity animatable 3D human avatars from a single image in second… | 52 | 2664 | 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 | 10652 | maintenance |
| Tencent/MimicMotion MimicMotion is a diffusion-based framework from Tencent for generating high-quality human motion videos guided by pose sequences, featuring… | 47 | 2647 | active |
| colour-science/colour Colour is an open-source Python library providing a comprehensive collection of colour science algorithms and datasets, including colour sp… | 74 | 2642 | active |
| ultralytics/yolov3 Ultralytics' PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection. It provides training, validation… | 67 | 10596 | maintenance |
| anliyuan/Ultralight-Digital-Human 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… | 64 | 2627 | active |
| swz30/Restormer Restormer is an efficient Transformer architecture for high-resolution image restoration, published as a CVPR 2022 Oral paper. It provides … | 44 | 2625 | stable |
| 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… | 88 | 2620 | active |
| antoinelame/GazeTracking A Python library that provides webcam-based eye tracking, returning pupil coordinates and gaze direction in real time using OpenCV and dlib… | 68 | 2619 | 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… | 42 | 2598 | active |
| Slicer/Slicer 3D Slicer is a free, open-source desktop platform for visualization, processing, segmentation, registration, and analysis of medical and bi… | 67 | 2595 | stable |
| 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… | 55 | 2589 | active |
| 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… | 54 | 2588 | 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 … | 58 | 2571 | active |
| 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 | 10223 | maintenance |
| advimman/lama LaMa is a PyTorch-based image inpainting model that fills large missing regions in images using fast Fourier convolutions, generalizing wel… | 34 | 10217 | maintenance |
| jolibrain/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 |
| 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 | 2547 | 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… | 36 | 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… | 29 | 2534 | 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 | 2529 | active |
| rpautrat/SuperPoint A TensorFlow (with PyTorch conversion) implementation of the SuperPoint self-supervised interest point detector and descriptor network. It … | 41 | 2511 | stable |
| luanfujun/deep-photo-styletransfer Reference implementation of the CVPR 2017 paper 'Deep Photo Style Transfer', performing photorealistic image style transfer using Torch wit… | 32 | 9989 | maintenance |
| BrunoLevy/geogram Geogram is a C++ programming library of geometric algorithms for geometry processing, including surface reconstruction, remeshing, Boolean … | 90 | 2499 | stable |
| yformer/EfficientSAM EfficientSAM is an efficient image segmentation model that leverages masked image pretraining to provide a lightweight alternative to Meta'… | 27 | 2491 | active |
| sthalles/SimCLR A PyTorch reference implementation of SimCLR, a self-supervised contrastive learning framework for learning visual representations from unl… | 23 | 2491 | stable |
| 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 | 2487 | active |
| ipazc/mtcnn A Python library implementing the MTCNN (Multitask Cascaded Convolutional Networks) algorithm for face detection and facial landmark alignm… | 23 | 2485 | stable |
| 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 | 2483 | active |
| QIN2DIM/hcaptcha-challenger A Python library that solves hCaptcha challenges using multimodal large language models and ONNX vision models (YOLO, CLIP, ResNet) integra… | 86 | 2482 | 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 | 9853 | maintenance |
| AprilRobotics/apriltag AprilTag is a small C library implementing a visual fiducial (marker) detection system, computing the precise 3D position, orientation, and… | 71 | 2480 | 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… | 41 | 2476 | active |
| wgsxm/PartCrafter PartCrafter is a structured 3D generative model that jointly generates multiple semantically meaningful 3D mesh parts and objects from a si… | 53 | 2471 | active |
| AngusJohnson/Clipper2 Clipper2 is a polygon clipping, offsetting, and triangulation library available in C++, C#, and Delphi. It performs boolean operations (int… | 77 | 2462 | 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 … | 20 | 2458 | 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 | 9737 | maintenance |
| 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 … | 63 | 2452 | 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… | 48 | 2442 | 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 | 9631 | maintenance |
| 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 | 2427 | 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… | 88 | 2426 | 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 … | 28 | 2421 | 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… | 63 | 2416 | 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… | 41 | 2416 | 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… | 69 | 2415 | 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… | 39 | 2411 | active |
| nv-tlabs/3dgrut NVIDIA's official implementations of 3D Gaussian Ray Tracing (3DGRT) and 3D Gaussian Unscented Transform (3DGUT), which render volumetric G… | 71 | 2390 | 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… | 61 | 2386 | active |
| ailia-ai/ailia-models A collection of 400+ pre-trained state-of-the-art AI models (object detection, pose estimation, speech recognition, LLMs, image generation,… | 77 | 2385 | 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… | 35 | 2375 | active |
| 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… | 88 | 2371 | 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… | 60 | 2370 | active |
| OpenGVLab/InternVideo InternVideo is a series of open-source video foundation models for multimodal video understanding, spanning generative and discriminative l… | 72 | 2368 | 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 | 2360 | 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… | 54 | 2353 | active |
| 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… | 48 | 2337 | stable |
| MouseLand/cellpose Cellpose is a generalist deep learning algorithm for cellular and nucleus segmentation in microscopy images, with human-in-the-loop capabil… | 86 | 2331 | active |