Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

TL;DR

Kornia is an open source, differentiable computer vision library built on PyTorch, enabling seamless integration of classical vision algorithms into neural networks with efficient auto-differentiation.

Contribution

It introduces a comprehensive set of differentiable vision modules inspired by OpenCV, facilitating the integration of classical vision techniques into deep learning models.

Findings

Provides a unified framework for classical and deep learning vision tasks

Achieves efficient performance leveraging PyTorch's auto-differentiation

Demonstrates competitive results in benchmark comparisons

Abstract

This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.