Ultralytics YOLO 🚀 for SOTA object detection, instance segmentation, semantic segmentation, depth estimation, classification, pose estimation, oriented object detection, and multi-object tracking.
Open Source Differentiable Computer Vision Library for PyTorch
Typed Python SDK for the Ultralytics Platform API
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations 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.
Low level implementations for computer vision in Rust
The Rerun Logging SDK
High-performance image processing functions for deep learning and computer vision.
Video scene cut/shot detection program and Python library (bundles the opencv-python OpenCV variant and the scenedetect CLI).
A set of easy-to-use utils that will come in handy in any Computer Vision project
A series of convenience functions to make basic image processing functions such as translation, rotation, resizing, skeletonization, displaying Matplotlib images, sorting contours, detecting edges, and much more easier with OpenCV and both Python 2.7 and Python 3.
Collection of common code shared among different research projects in FAIR computer vision team
QUick and DIrty Domain Adaptation
Document Text Recognition (docTR): deep Learning for high-performance OCR on documents.
Image augmentation library for deep neural networks
Open Source Image and Video Super-Resolution Toolbox
Microsoft Azure Cognitive Services Computer Vision Client Library for Python
A toolkit for making real world machine learning and data analysis applications
Video scene cut/shot detection program and Python library (bundles the opencv-python-headless OpenCV variant and the scenedetect CLI; for servers without GUI libraries).
FiftyOne: the open-source tool for building high-quality datasets and computer vision models
Generalizable Perception Stack for 3D, 4D, spatial AI and scene understanding
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration
Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volume data, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows. Available under AGPL-3.0-only or a commercial license with agreed coverage for your team, products, and deployments.
Conversions between kornia and other computer vision libraries formats
RF100-VL Dataset Interface
OpenMMLab Detection Toolbox and Benchmark
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration
Provides spatial maths capability for Python.
A unified, high-performance computer vision tracking library.
OpenMMLab Computer Vision Foundation
A toolkit for making real world machine learning and data analysis applications
Python SDK and CLI for Pictograph: real-time vision tools for agents and developers. SAM3 labeling, RF-DETR and YOLOX training, TensorRT GPU endpoints, and live video streams.
OpenMMLab Computer Vision Foundation
With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference.
Perception evaluation toolkit — pycocotools-compatible detection metrics and panoptic quality in pure Rust, up to 113× faster
Light Weight Toolkit for Bounding Boxes
Mahotas: Computer Vision Library
Ultralytics YOLO 🚀 for SOTA computer vision in server, container, and headless environments.
SDK for the Reality Defender deepfake detection API
Onnx Text Recognition (OnnxTR) OCR plugin for docling
High-performance, parity-preserving COCO-style evaluation
Reproducible pet re-identification: dataset audits, embeddings, metric learning and evaluation
Pre-trained image models using ONNX for fast, out-of-the-box inference.
A tool for converting computer vision label formats.
UniFace: A Unified Face Analysis Library for Python
Different ways of visualizing objects given bounding box data
Implementation of some color correction / automatic white balance algorithms
Easily turn a set of image urls to an image dataset
MCP server exposing FiftyOne dataset analysis tools