
U-Net
A convolutional network architecture for fast and precise image segmentation, particularly in biomedical applications.
Discover the strongest tools and workflows for object detection.

A convolutional network architecture for fast and precise image segmentation, particularly in biomedical applications.

A dataset for Large Vocabulary Instance Segmentation.
Robust Associations Multi-Pedestrian Tracking using motion and appearance information with camera-motion compensation.
Efficient and lightweight CNN architecture for mobile and edge devices.
A comprehensive set of computer vision transformations for data augmentation and manipulation in PyTorch.

Hierarchical Vision Transformer using Shifted Windows for general-purpose computer vision tasks.

The world's most comprehensive open-source library for real-time computer vision and machine learning.

Pro-level video editing powered by advanced generative AI for creators and businesses.

A comprehensive real-time streaming analytics toolkit for AI-based multi-sensor processing and video understanding.
Integrate powerful vision detection features into applications for image analysis, document understanding, and video intelligence.
Discover and deploy pre-trained AI models for fashion-related tasks.
Pre-trained Vision Transformer models for fashion image classification and analysis.
Automate image recognition and video analysis with pre-trained and customizable computer vision APIs, lowering costs and accelerating insights.
Integrate powerful vision detection features into applications for image analysis and understanding.
Accelerate deep learning inference across Intel hardware for edge and cloud deployment.
Enterprise-grade AI integrated directly into your database and business applications with zero data leakage.

A suite of libraries, tools, and APIs for applying AI and ML techniques across multiple platforms and modalities.

Turning global physical data into actionable geospatial intelligence with AI-driven computer vision.