Kornia — Geometric Computer Vision Library

Kornia

Kornia is a differentiable computer vision library on top of PyTorch. Every operation — from homography estimation to image augmentation — is implemented as a differentiable module, making it ideal for learning-based vision pipelines and end-to-end training.

Key Features

• Geometry: camera models, homographies, epipolar geometry, pose estimation
• Image processing: filtering, colour space conversion, morphology, edge detection
• Augmentation: photometric and geometric transforms for training data
• Feature extraction: SIFT, LoFTR, DISK, KeyNet, SOLD2 descriptors
• 3D vision: depth, point clouds, quaternions, rotation groups (SO3/SE3)
• Fully differentiable — gradients flow through every op

Quick Start

import torch
import kornia
import kornia.augmentation as K

# Differentiable augmentation pipeline
aug = K.AugmentationSequential(
    K.RandomHorizontalFlip(p=0.5),
    K.ColorJitter(0.2, 0.2, 0.2, 0.2),
    K.RandomGaussianBlur((3, 3), (0.1, 2.0)),
    data_keys=["input", "bbox"],
)
tensor = torch.rand(2, 3, 256, 256)
out = aug(tensor)

Install via ai-supply

npx ai-supply add kornia-geometric-vision-library

Curated mirror of the open-source Kornia (Apache-2.0). Get it from the source.