CNN-based affine shape estimator.
AffNet model implementation in PyTorch for ECCV2018 paper "Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability"
The master branch is the one, which produced ECCV-paper results, python 2.7 and pytorch 0.4.0
Here is the one, which successfully runs on python 3.7, pytorch 1.4.0
AffNet generates up to twice more correspondeces compared to Baumberg iterations
| Detector + Descriptor | BoW | BoW + SV | BoW + SV + QE | HQE + MA |
|---|---|---|---|---|
| HesAff + RootSIFT | 55.1 | 63.0 | 78.4 | 88.0 |
| HesAff + HardNet++ | 60.8 | 69.6 | 84.5 | 88.3 |
| HesAffNet + HardNet++ | 68.3 | 77.8 | 89.0 | 89.5 |
To download datasets and start learning affnet:
git clone https://github.com/ducha-aiki/affnet
./run_me.shTo reproduce Figure 1 in paper, run notebook
To reproduce Figure 2-3 in paper, run notebooks here
git clone https://github.com/ducha-aiki/affnet
./run_me.shPre-trained models can be found in folder pretrained: AffNet.pth
We provide two examples, how to estimate affine shape with AffNet. First, on patch-column file, in HPatches format, i.e. grayscale image with w = patchSize and h = nPatches * patchSize
cd examples/just_shape
python detect_affine_shape.py imgs/face.png out.txt
Out file format is upright affine frame a11 0 a21 a22
Second, AffNet inside pytorch implementation of Hessian-Affine
2000 is number of regions to detect.
cd examples/hesaffnet
python hesaffnet.py img/cat.png ells-affnet.txt 2000
python hesaffBaum.py img/cat.png ells-Baumberg.txt 2000
output ells-affnet.txt is Oxford affine format
1.0
128
x y a b c
Example is in [notebook](examples/hesaffnet/WBS demo.ipynb)
Please cite us if you use this code:
@inproceedings{AffNet2017,
author = {Dmytro Mishkin, Filip Radenovic, Jiri Matas},
title = "{Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability}",
year = 2018,
month = sep,
booktitle = {Proceedings of ECCV}
}