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 ----------------- .. image:: https://github.com/kornia/data/raw/main/kornia_paper_mosaic.png :align: center 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 | +-----------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+