Kornia: an open source differentiable computer vision library for PyTorch

E. Riba, D. Mishkin, D. Ponsa, E. Rublee, G. Bradski. Kornia: an open source differentiable computer vision library for PyTorch. pages 3674-3683, DOI https://doi.org/10.1109/WACV45572.2020.9093363, 5, 2020.

Autoren
  • Edgar Riba
  • Dmytro Mishkin
  • Daniel Ponsa
  • Ethan Rublee
  • Gary Bradski
BuchProceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
TypKonferenzband
DOIhttps://doi.org/10.1109/WACV45572.2020.9093363
ISBN978-1-7281-6553-0
Monat5
Jahr2020
Seiten3674-3683
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. 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.