---
license: mit
tags:
  - kornia
  - affine-shape-estimation
  - feature-detection
---

# kornia/affnet

Pretrained weights for **AffNet**,
used by [`kornia.feature.LAFAffineShapeEstimator`](https://kornia.readthedocs.io/en/latest/feature.html).

AffNet is a CNN that estimates the 2×2 affine shape matrix for a detected keypoint patch,
making subsequent description invariant to affine transformations. Trained jointly with
HardNet to maximise discriminability of affine-normalised patches. ECCV 2018.

**Original repo:** [ducha-aiki/affnet](https://github.com/ducha-aiki/affnet)

## Weights

| File | Description |
|------|-------------|
| `AffNet.pth` | Default checkpoint |

## Citation

```bibtex
@inproceedings{AffNet2018,
    author    = {D. Mishkin and F. Radenovic and J. Matas},
    title     = {{Repeatability is Not Enough}: Learning Affine Regions
                 via Discriminability},
    booktitle = {ECCV},
    year      = {2018}
}
```