Kornia Models#
Kornia ships a curated set of model architectures, each wrapped as a regular nn.Module. Most of them come with
pretrained weights that are downloaded on first use; MobileViT ships as an architecture only, for training or for
loading your own checkpoint. Each page below opens with the shortest script that runs the model, shows what it
returns on a real input, and ends with the paper. The builders that construct the models are documented on the
kornia.models API page, and the local-feature models under kornia.feature.
Model |
Task |
Venue |
Licence |
|---|---|---|---|
Object detection |
arXiv 2023 |
Apache-2.0 |
|
Face detection |
IEEE TIP 2021 |
Apache-2.0 |
|
Promptable segmentation |
ICCV 2023 |
Apache-2.0 |
|
Promptable segmentation (lightweight) |
arXiv 2023 |
Apache-2.0 |
|
Segmentation, classification, detection backbone |
ICCV 2023 |
Apache-2.0 |
|
Image classification backbone |
ICLR 2021 |
Apache-2.0 |
|
Image classification backbone (mobile) |
ICLR 2022 |
– |
|
Image classification backbone (small) |
ECCV 2022 |
– |
|
Image matching (detector-free) |
CVPR 2021 |
Apache-2.0 |
|
Local feature descriptor |
NeurIPS 2017 |
MIT |
|
Affine shape estimation for local features |
ECCV 2018 |
MIT |
|
Line detection and matching |
CVPR 2021 |
MIT |
|
Edge detection |
WACV 2020 |
MIT |
|
Enhancement – video deblurring of fast-moving objects |
CVPR 2021 |
Apache-2.0 |