This work presents Kornia – an open source computer
vision library which consists of a set of differentiable rou-
tines and modules to solve generic computer vision prob-
lems. 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 com-
posed of a set of modules containing operators that can be
inserted inside neural networks to train models to perform
image transformations, camera calibration, epipolar geom-
etry, 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 pro-
vided including a benchmark comparing to existing vision
libraries.
Referensi
- https://arxiv.org/pdf/1910.02190.pdf
- https://github.com/kornia/kornia
- https://twitter.com/kornia_foss