Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)
Best Computer Vision Tools AI GitHub Repos illustration – ToolPotion.ai

Best Computer Vision Tools AI GitHub Repos

37 tools

Discover the best AI GitHub Repos — from personal AI assistants and workflow automation platforms to machine learning frameworks, open-source coding agents, and model-definition tools, this is where developers find resources that streamline their daily tasks: building intelligent assistants, automating workflows, developing machine learning models, and managing source code collaboration. Browse 37 AI GitHub Repos spanning AI Agent Builders, AI Models & LLMs, AI Coding Assistants, Machine Learning Platforms and MLOps & Model Deployment and more.

AI GitHub Repos

Powerful, lightweight OCR toolkit designed to convert PDFs and image documents into structured data for AI applications. It supports over 100 languages and bridges…PaddleOCR is a powerful, lightweight OCR toolkit designed to convert PDFs and image documents into structured data for AI applications. It supports over 100 languages and bridges…

Computer Vision Tools
Ranked #14 in AI GitHub Repos

AI GitHub Repos

Includes YOLO26, YOLO11, and YOLOv8, providing capabilities for object detection, instance segmentation, semantic segmentation, image classification, pose…Ultralytics YOLO includes YOLO26, YOLO11, and YOLOv8, providing capabilities for object detection, instance segmentation, semantic segmentation, image classification, pose…

FeaturedComputer Vision Tools
Ranked #18 in AI GitHub Repos

AI GitHub Repos

Platform designed for object detection, segmentation, and various visual recognition tasks. Developed by Facebook Research, it provides advanced tools for…Detectron2 is a platform designed for object detection, segmentation, and various visual recognition tasks. Developed by Facebook Research, it provides advanced tools for…

Computer Vision ToolsHealthcare & Life Sciences
Ranked #113 in AI GitHub Repos

AI GitHub Repos

FiftyOne is an open-source tool for refining high-quality datasets and visual AI models. It allows developers to manage, visualize, and analyze datasets efficiently, enhancing AI…

Computer Vision Tools
Ranked #128 in AI GitHub Repos

AI GitHub Repos

Lightweight library for Python that offers face recognition and facial attribute analysis, including age, gender, emotion, and race detection. It is designed to be…DeepFace is a lightweight library for Python that offers face recognition and facial attribute analysis, including age, gender, emotion, and race detection. It is designed to be…

Computer Vision Tools
Ranked #135 in AI GitHub Repos

AI GitHub Repos

Real-time open-vocabulary object detection tool developed by AILab-CVC. It aims to enhance object detection capabilities by allowing detection of objects not seen…YOLO-World is a real-time open-vocabulary object detection tool developed by AILab-CVC. It aims to enhance object detection capabilities by allowing detection of objects not seen…

Computer Vision Tools
Ranked #142 in AI GitHub Repos

AI GitHub Repos

Lightweight tool designed for labeling 3D bounding boxes in point clouds. It is ideal for developers and researchers working with 3D data, providing an efficient…labelCloud is a lightweight tool designed for labeling 3D bounding boxes in point clouds. It is ideal for developers and researchers working with 3D data, providing an efficient…

Computer Vision ToolsAutomotive
Ranked #219 in AI GitHub Repos

AI GitHub Repos

GitHub repository by Baidu focused on optical character recognition. It introduces one-shot long-horizon parsing, aiming to enhance OCR capabilities…Unlimited OCR is a GitHub repository by Baidu focused on optical character recognition. It introduces one-shot long-horizon parsing, aiming to enhance OCR capabilities…

FeaturedComputer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

TensorFlow implementation for face recognition and clustering, based on the FaceNet paper. It leverages deep learning models to generate unified embeddings for faces,…FaceNet is a TensorFlow implementation for face recognition and clustering, based on the FaceNet paper. It leverages deep learning models to generate unified embeddings for faces,…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

AI model that enhances Vision Transformer (ViT) performance for dense prediction tasks like object detection and segmentation. It introduces image-specific…ViT-Adapter is an AI model that enhances Vision Transformer (ViT) performance for dense prediction tasks like object detection and segmentation. It introduces image-specific…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

The Vision Transformer (ViT) repository provides models and code for image recognition tasks. It includes implementations of the Vision Transformer and MLP-Mixer architectures,…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Region-based object detection framework that utilizes fully convolutional networks for accurate and efficient image analysis. It shares computation across the entire…R-FCN is a region-based object detection framework that utilizes fully convolutional networks for accurate and efficient image analysis. It shares computation across the entire…

Computer Vision Tools
See the Top 250 AI GitHub Repos

Deep learning model architecture that adaptively recalibrates channel-wise feature responses. It enhances performance by explicitly…Squeeze-and-Excitation Networks (SENet) is a deep learning model architecture that adaptively recalibrates channel-wise feature responses. It enhances performance by explicitly…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

GitHub project designed to verify AI-generated product imagery, ensuring it preserves the real packaging. It uses SIFT/RANSAC inlier gate to provide a PASS/FAIL…Packfix is a GitHub project designed to verify AI-generated product imagery, ensuring it preserves the real packaging. It uses SIFT/RANSAC inlier gate to provide a PASS/FAIL…

Computer Vision ToolsRetail & Consumer Goods
See the Top 250 AI GitHub Repos

AI GitHub Repos

Real-time multi-person keypoint detection library developed by the CMU Perceptual Computing Lab. It estimates keypoints for body, face, hands, and feet, enabling…OpenPose is a real-time multi-person keypoint detection library developed by the CMU Perceptual Computing Lab. It estimates keypoints for body, face, hands, and feet, enabling…

Computer Vision Tools
See the Top 250 AI GitHub Repos

Versatile video labeling GUI in Python, integrating state-of-the-art detector and tracker. It aids in efficient video annotation, enhancing productivity for…UltimateLabeling is a versatile video labeling GUI in Python, integrating state-of-the-art detector and tracker. It aids in efficient video annotation, enhancing productivity for…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Open-source online platform designed for collaborative image labeling. It facilitates teamwork in annotating images, making it ideal for projects requiring…ImageTagger is an open-source online platform designed for collaborative image labeling. It facilitates teamwork in annotating images, making it ideal for projects requiring…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Open-source GitHub project, based on the approach published in the "Visual ChatGPT" paper, that connects ChatGPT to visual foundation models so it can send and…TaskMatrix is an open-source GitHub project, based on the approach published in the "Visual ChatGPT" paper, that connects ChatGPT to visual foundation models so it can send and…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Offers a reference PyTorch implementation and models, developed by Facebook Research. It is designed for researchers and developers interested in leveraging self-supervised…DINOv3 offers a reference PyTorch implementation and models, developed by Facebook Research. It is designed for researchers and developers interested in leveraging self-supervised…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

State-of-the-art AI tool developed by Facebook Research. It specializes in image and video CLIP models and multimodal large language models, offering…Perception Encoder is a state-of-the-art AI tool developed by Facebook Research. It specializes in image and video CLIP models and multimodal large language models, offering…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Multi-object tracking tool that associates every detection box to enhance tracking accuracy. Developed for ECCV 2022, it is designed to improve object tracking in…ByteTrack is a multi-object tracking tool that associates every detection box to enhance tracking accuracy. Developed for ECCV 2022, it is designed to improve object tracking in…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Official implementation of the paper 'Marrying DINO with Grounded Pre-Training for Open-Set Object Detection'. It aims to enhance object detection…Grounding DINO is the official implementation of the paper 'Marrying DINO with Grounded Pre-Training for Open-Set Object Detection'. It aims to enhance object detection…

Computer Vision Tools
See the Top 250 AI GitHub Repos

Robust multi-pedestrian tracking tool designed to enhance the accuracy of tracking systems. It focuses on improving associations in tracking scenarios, making it a…BoT-SORT is a robust multi-pedestrian tracking tool designed to enhance the accuracy of tracking systems. It focuses on improving associations in tracking scenarios, making it a…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Implementation of the paper 'You Only Learn One Representation: Unified Network for Multiple Tasks'. It aims to provide a unified network for handling multiple tasks…YOLOR is an implementation of the paper 'You Only Learn One Representation: Unified Network for Multiple Tasks'. It aims to provide a unified network for handling multiple tasks…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Official code implementation of General OCR Theory, aiming to advance OCR technology through a unified end-to-end model. It is hosted on GitHub and provides…GOT-OCR 2.0 is an official code implementation of General OCR Theory, aiming to advance OCR technology through a unified end-to-end model. It is hosted on GitHub and provides…

Computer Vision Tools
See the Top 250 AI GitHub Repos

Web-based tool designed to streamline image annotation processes. It allows users to design custom annotation workflows, enhancing efficiency and accuracy in labeling…LOST is a web-based tool designed to streamline image annotation processes. It allows users to design custom annotation workflows, enhancing efficiency and accuracy in labeling…

Computer Vision ToolsHealthcare & Life Sciences
See the Top 250 AI GitHub Repos

AI GitHub Repos

Tool designed to convert computer vision label formats efficiently. It supports various formats, making it easier for developers to manage and transform labels…LabelFormat is a tool designed to convert computer vision label formats efficiently. It supports various formats, making it easier for developers to manage and transform labels…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Deep learning model for object detection and instance segmentation, implemented in Keras and TensorFlow. It is designed to identify and segment objects within…Mask R-CNN is a deep learning model for object detection and instance segmentation, implemented in Keras and TensorFlow. It is designed to identify and segment objects within…

Computer Vision ToolsHealthcare & Life Sciences
See the Top 250 AI GitHub Repos

AI GitHub Repos

JavaFX desktop application designed for creating image-object annotations using bounding boxes. It facilitates precise annotation tasks, making it ideal…Bounding Box Editor is a JavaFX desktop application designed for creating image-object annotations using bounding boxes. It facilitates precise annotation tasks, making it ideal…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Anomaly detection library featuring state-of-the-art algorithms. It offers experiment management, hyper-parameter optimization, and edge inference capabilities,…Anomalib is an anomaly detection library featuring state-of-the-art algorithms. It offers experiment management, hyper-parameter optimization, and edge inference capabilities,…

Computer Vision ToolsManufacturing & Industrial
See the Top 250 AI GitHub Repos

AI GitHub Repos

GitHub project focused on creating reusable computer vision tools. It allows developers to contribute and enhance their computer vision capabilities through…Supervision is a GitHub project focused on creating reusable computer vision tools. It allows developers to contribute and enhance their computer vision capabilities through…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Versatile web-based visual data annotation tool designed to streamline the process of labeling and managing datasets. It supports various annotation types, making it…Scalabel is a versatile web-based visual data annotation tool designed to streamline the process of labeling and managing datasets. It supports various annotation types, making it…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Open-source image annotation tool designed for efficient dataset creation. It features an intuitive interface and flexible export options, streamlining machine…Annotate Lab is an open-source image annotation tool designed for efficient dataset creation. It features an intuitive interface and flexible export options, streamlining machine…

Computer Vision ToolsHealthcare & Life Sciences
See the Top 250 AI GitHub Repos

AI GitHub Repos

Open-source optical character recognition engine. It supports multiple languages and can be used for text extraction from images. Ideal for developers seeking…Tesseract OCR is an open-source optical character recognition engine. It supports multiple languages and can be used for text extraction from images. Ideal for developers seeking…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Open-source project that introduces scalable pixel-native search, aiming to revolutionize web parsing. It offers a new approach to handling and searching pixel data…PixelRAG is an open-source project that introduces scalable pixel-native search, aiming to revolutionize web parsing. It offers a new approach to handling and searching pixel data…

Computer Vision Tools
See the Top 250 AI GitHub Repos

AI GitHub Repos

Agent skill that determines the location where a photo was taken using OpenStreetMap geometry, elevation skylines, satellite imagery, and street view. It…Geo-Sleuth is an agent skill that determines the location where a photo was taken using OpenStreetMap geometry, elevation skylines, satellite imagery, and street view. It…

Computer Vision Tools
See the Top 250 AI GitHub Repos

24 of 37

Know a standout that belongs in AI GitHub Repos?

ToolPotion is the AI tools directory people browse to find the best AI GitHub Repos. Listing is free and every submission is editor-reviewed — put your tool where the search starts.

Submit a GitHub Repo