Kornia is a differentiable computer vision library built on PyTorch. It provides image-processing and geometric-vision operations that integrate with machine-learning pipelines, supporting automatic differentiation, batch processing and GPU acceleration.
The library includes more than 500 operations spanning image enhancement, filtering, augmentation, feature detection, geometry, stereo vision, image registration, pose estimation, optical flow and 3D vision. It also offers pretrained models for tasks such as face detection, feature matching, segmentation and image classification.
This is free and open source software.
Key Features
- Provides differentiable image-processing and computer-vision operations.
- Integrates directly with PyTorch and its automatic differentiation system.
- Supports batched transformations and GPU acceleration.
- Offers affine, perspective, homography, resizing and other geometric transformations.
- Includes Gaussian, median, bilateral, Sobel, Canny and other filters.
- Provides configurable image, video and patch augmentation pipelines.
- Supports AutoAugment, RandAugment, TrivialAugment, MixUp and CutMix.
- Includes feature detectors, descriptors and matching algorithms.
- Provides camera calibration, stereo vision and epipolar geometry tools.
- Supports image registration, pose estimation, optical flow and point-cloud operations.
- Includes vision-specific loss functions, metrics and neural-network layers.
- Offers pretrained models including LoFTR, LightGlue, SAM, MobileViT and Vision Transformer.
- Supports exporting and running compatible models with ONNX.
Website: github.com/kornia/kornia
Support:
Developer: Edgar Riba
License: Apache License 2.0
Kornia is written in Python. Learn Python with our recommended free books and free tutorials.
Related Software
| Image Processing Libraries | |
|---|---|
| matplotlib | Python 2D plotting library |
| OpenCV | Library that includes several hundreds of computer vision algorithms |
| VIPS | Fast image processing library with low memory requirements |
| SciPy | Scientific Computing Tools for Python |
| Pillow | Fork of the Python Imaging Library |
| Pillow-SIMD | Highly optimized downstream Pillow fork |
| scikit-image | Collection of algorithms for image processing |
| Kornia | Differentiable computer vision library |
| ImageMagick | Uses multiple computational threads to increase performance |
| GraphicsMagick | Billed as the Swiss army knife of image processing. |
| GEGL | Generic Graphics Library |
| OpenImageIO | Library and utilities for reading, writing and processing image files |
| CImg | Lightweight C++ toolkit for developing image-processing applications |
| Mahotas | Library of fast computer vision algorithms |
| SimpleITK | Image analysis toolkit with a large number of components |
| Netpbm | Toolkit for manipulation of graphic images |
| LibGD | Library for the dynamic creation of images by developers |
Read our verdict in the software roundup.
 Explore our carefully curated directory of recommended free and open source software, covering every major software category.The directory forms part of our extensive collection of articles for Linux enthusiasts. It includes hundreds of detailed reviews, together with free and open source alternatives to proprietary software from companies such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. LinuxLinks also covers interesting projects worth exploring, Linux-compatible hardware, free programming books and tutorials, and much more. Know a useful free and open source Linux application that we haven’t covered? Tell us about it using our submission form. |
Please read our Comment Policy before commenting.