Highlighted Features

At Kornia, we are dedicated to pushing the boundaries of computer vision by providing a robust, efficient, and versatile toolkit. Our library is built on the powerful PyTorch backend, leveraging its efficiency and auto-differentiation capabilities to deliver high-performance solutions for a wide range of vision tasks.

Accessible AI Models

We are excited to announce our latest advancement: a new initiative designed to seamlessly integrate lightweight AI models into Kornia. This addition is crafted to empower developers, researchers, and enthusiasts to harness the full potential of accessible AI, simplifying complex vision tasks and accelerating innovation.

We have curated a selection of lightweight AI models, including YuNet, Loftr, and SAM, optimized for performance and efficiency. These models offer efficient computations that do not require expensive GPUs, making cutting-edge AI accessible to everyone. We welcome the whole community of developers and researchers who are passionate about advancing computer vision, throwing PRs for your lightning fast models!

Classic Operators

At a granular level, Kornia is a library that consists of the following components:

Component	Description
kornia	a Differentiable Computer Vision library like OpenCV, with strong GPU support
kornia.augmentation	a module to perform data augmentation in the GPU
kornia.color	a set of routines to perform color space conversions
kornia.contrib	a compilation of user contrib and experimental operators
kornia.feature	a module to perform feature detection
kornia.filters	a module to perform image filtering and edge detection
kornia.geometry	a geometric computer vision library to perform image transformations, 3D linear algebra and conversions using different camera models
kornia.losses	a stack of loss functions to solve different vision tasks
kornia.morphology	a module to perform morphological operations
kornia.utils	image to tensor utilities and metrics for vision problems