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
Low level implementations for computer vision in Rust
The Rerun Logging SDK
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.
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
Document Text Recognition (docTR): deep Learning for high-performance OCR on documents.
QUick and DIrty Domain Adaptation
Open Source Image and Video Super-Resolution Toolbox
Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
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).
Image augmentation library for deep neural networks
Microsoft Azure Cognitive Services Computer Vision Client Library for Python
A toolkit for making real world machine learning and data analysis applications
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.
RF100-VL Dataset Interface
FiftyOne: the open-source tool for building high-quality datasets and computer vision models
OpenMMLab Detection Toolbox and Benchmark
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration
The unified multimodal backend agents build with. Database, orchestration, and serving in one Python file.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration
Provides spatial maths capability for Python.
Generalizable Perception Stack for 3D, 4D, spatial AI and scene understanding
Onnx Text Recognition (OnnxTR) OCR plugin for docling
A toolkit for making real world machine learning and data analysis applications
Conversions between kornia and other computer vision libraries formats
HPSv3: Towards Wide-Spectrum Human Preference Score - A VLM-based preference model for image quality assessment
A CLI tool to edit PDF slides using natural language prompts, powered by Gemini 3 Pro Image
OpenMMLab Computer Vision Foundation
Perception evaluation toolkit — pycocotools-compatible detection metrics and panoptic quality in pure Rust, up to 113× faster
OpenMMLab Computer Vision Foundation
SDK for the Reality Defender deepfake detection API
High-performance, parity-preserving COCO-style evaluation
Light Weight Toolkit for Bounding Boxes
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.
Mahotas: Computer Vision Library
Pre-trained image models using ONNX for fast, out-of-the-box inference.
Ultralytics YOLO 🚀 for SOTA computer vision in server, container, and headless environments.
A tool for converting computer vision label formats.
OpenMMLab Pose Estimation Toolbox and Benchmark.
UniFace: A Unified Face Analysis Library for Python
MCP server exposing FiftyOne dataset analysis tools
Open MMLab Semantic Segmentation Toolbox and Benchmark
Easily turn a set of image urls to an image dataset