Numpy-native operator library for vision, 3-D and measurement (3,838 typed ops in the machine-readable index: imaging, point clouds, optics, tomography, metrology) with an evolutionary pipeline designer and honest holdout gating
Hardware Abstraction Layer for edge AI with zero-copy tensors, image processing, and YOLO decoding
Computer use for Hyprland: semantic desktop state over IPC plus vision and native Wayland input, in one MCP server
CellProfiler is a free open-source software designed to enable biologists without training in computer vision or programming to quantitatively measure phenotypes from thousands of images automatically.
Vision-driven computer-use engine for UI-native automation.
cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.
PlantCV: Plant phenotyping with computer vision
Cut agent token burn with zero accuracy loss on SWE-bench Verified. Local <3ms AST shield, Apple Silicon vision & memory runtime for Claude Code, Cursor & Antigravity.
阿里云百炼-通义万相图像生成MCP服务器
SuperGradients
Fast unique-color and per-color mask extraction for color-coded segmentation masks
Manipulate run-length-encoded image masks
Production-ready, type-safe dataset management, YOLO parsing, and caching utilities for computer vision pipelines
A fast AprilTag detector for every tag family, with sub-pixel corners and poses with covariances
Approximate image retrieval using ORB descriptors and FAISS IVF indexing.
CUDA-accelerated Computer Vision algorithms
Model Context Protocol server for AlbumentationsX augmentation previews, validation, and segmentation review.
Tool for finding and extracting motion events in video files (e.g. security camera footage).
Small cv2/Pillow image-processing utilities (load/save, resize/rotate/crop, blur/sharpen/edge, drawing) — standalone module from the SciTeX ecosystem
Morphological operations with CUDA acceleration
Computer vision processing library for visualizing and analyzing detection results from ML models
Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.
Geometry-safe spherical image processing and projection for computer-vision applications.
Infinite Photorealistic Worlds using Procedural Generation
Package for building OpenCV 4.5.4 including Python 3 bindings from the official sources.
Fork of Albumentations in direct support of NRTK (Natural Robustness Toolkit). Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows.
Control drones, robots and test rigs connected in the koebelt/dash app from Python.
High-performance Google Lens reverse image search, visual match scraper, and OCR extraction engine for Python.
Re-identification model stack for appearance embeddings
Unified high-performance Python toolkit for file operations, archives, configuration, dataset management, and zero-shot object detection pipelines.
Savant Rust core functions library
doc2text drastically improves the extraction of text from images by fixing resolution, text area (crop), and skew.
Visiongraph is a computer-vision pipeline library designed to simplify the prototyping of image-based algorithms
An open-source computer vision framework for wildlife image analysis, featuring state-of-the-art models for species classification and detection.
VisiMac - High-Performance Deep Learning, Computer Vision & Dataset Preparation Engine
Uncertainty quantification benchmark for VLM GUI grounding agents.
High-performance video streaming SDK for RocketWelder services using ZeroBuffer IPC
OpenVINO™ Training Extensions: Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
Controle de cursor por gestos da mao via webcam, com holograma 3D opcional.
Easy real-time object detection you can ship: real-time DETR detectors (ed-n … ed-x) with PyTorch training, OpenVINO inference on CPU/GPU/NPU, and a browser app to label and train. Apache-2.0 throughout.
A lightweight Computer Vision library for high-performance AI research - Modern Computer Vision on the Fly.
Mathematical Morphology module for PyTorch (CUDA), providing differentiable operators and learnable network layers.
Final release, no longer maintained: switch to sparrow-engine. PyTorch-Wildlife: open-source AI framework for camera-trap detection and species classification.
Toolkit for converting horizontal bounding boxes to oriented bounding boxes using segmentation models and evaluation of the conversion against ground truth.
Sipeed Maix Vision Python SDK
Tensorflow keras computer vision attention models. Alias kecam. https://github.com/leondgarse/keras_cv_attention_models
Unified Next-Gen Hardware Orchestration & AI Acceleration Runtime for Mobile & Edge
Structure from Motion toolkit built on COLMAP: a CLI, file formats and a 3D viewer
BNNR: XAI-driven augmentation & diagnostics for PyTorch vision - find model failures, fix with saliency-guided augmentation (ICD/AICD), prove with auditable reports.