Find tools › Open-source projects › Images, video & voice

kornia

Open-source project · by kornia

A Python toolkit for editing, transforming, and analyzing images directly on your graphics card using AI math.

For developersPopular3,027,336 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Augment image datasets directly on your graphics card
  • Calculate camera geometry and 3D point projections
  • Detect and match visual features across images

How to start

  1. Install the library using pip install kornia.

  2. Import Kornia operations into your PyTorch project.

  3. Pass image tensors to Kornia functions to process batches on your graphics card.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

A differentiable computer vision and spatial AI library built on PyTorch for image processing and geometry directly on the GPU.

Standard computer vision libraries like OpenCV force data transfers back to the CPU and cannot compute neural network gradients. Reach for Kornia when you need fast, batched image filters, camera geometry, or data augmentations on your graphics card.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-01. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map