kornia
A differentiable computer vision library for PyTorch, providing geometric vision and image processing algorithms for AI workflows.
What is kornia?
Kornia is a differentiable computer vision library built on PyTorch that provides a rich set of image processing and geometric vision algorithms. It enables seamless integration of classic computer vision techniques into deep learning pipelines, supporting tasks like image transformations, augmentations, and AI-driven vision models. The library focuses on making these operations differentiable and GPU-accelerated for modern AI workflows.
Researchers and developers working on computer vision and deep learning projects, particularly those using PyTorch who need differentiable vision operators, data augmentation pipelines, or pre-trained vision models.
Developers choose Kornia for its deep integration with PyTorch, providing a comprehensive suite of differentiable vision operations that are not available in standard deep learning frameworks. Its unique selling point is bringing traditional computer vision algorithms into the differentiable programming paradigm, enabling end-to-end trainable vision systems.
Overview
🐍 Geometric Computer Vision Library for Spatial AI
Use Cases
Best For
- Integrating differentiable image processing operators into PyTorch deep learning models
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
