Kornia
- Software
- Perception
- Library
Kornia is a differentiable computer vision library built on PyTorch, offering image processing, augmentation, geometry and pretrained AI models that integrate into deep learning workflows.
Made by Kornia, Spain (checked on github.com/kornia (opens in a new tab)).
Source on GitHub: github.com/kornia/kornia (opens in a new tab). Facts read at commit 5bb2354 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 5bb2354 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Provides differentiable image processing operators such as filters, geometric transformations, enhancements and edge detection.
- Offers augmentation pipelines, including sequential, patch and video variants, plus automatic augmentation policies.
- Includes geometry tools for camera models, stereo vision, homography, epipolar geometry and pose estimation.
- Ships pretrained AI models for face detection, feature matching, feature description, segmentation and classification.
- Supports batch transformations, auto-differentiation and GPU acceleration through PyTorch.
- Includes ONNX chaining utilities and half-precision (float16/bfloat16) support with documented known failures on CPU and CUDA.
Written by Robotheca from the project's README (opens in a new tab) at commit 5bb2354.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 16 Oct 2026 on main
- Latest release
- v0.8.3 (19 May 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.