Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, Gary Bradski; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 3674-3683

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. At its core, 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 also provided including a benchmark comparing to existing vision libraries.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Riba_2020_WACV,
author = {Riba, Edgar and Mishkin, Dmytro and Ponsa, Daniel and Rublee, Ethan and Bradski, Gary},
title = {Kornia: an Open Source Differentiable Computer Vision Library for PyTorch},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}