Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00341237" target="_blank" >RIV/68407700:21230/20:00341237 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/WACV45572.2020.9093363" target="_blank" >https://doi.org/10.1109/WACV45572.2020.9093363</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV45572.2020.9093363" target="_blank" >10.1109/WACV45572.2020.9093363</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2020 IEEE Winter Conference on Applications of Computer Vision (WACV)

ISBN

978-1-7281-6553-0

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

10

Strana od-do

3663-3672

Název nakladatele

IEEE

Místo vydání

New Jersey

Místo konání akce

Snowmass village

Datum konání akce

1. 3. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000578444803078