https://github.com/cvlab-epfl/LIFT
Code release for the ECCV 2016 paper
https://github.com/cvlab-epfl/LIFT
Last synced: 29 days ago
JSON representation
Code release for the ECCV 2016 paper
- Host: GitHub
- URL: https://github.com/cvlab-epfl/LIFT
- Owner: cvlab-epfl
- Created: 2016-07-22T12:49:15.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2017-11-06T13:55:43.000Z (over 7 years ago)
- Last Synced: 2024-08-03T01:15:14.340Z (10 months ago)
- Language: Python
- Homepage:
- Size: 35.9 MB
- Stars: 485
- Watchers: 57
- Forks: 168
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-image-alignment-and-stitching - **2016ECCV** - epfl/tf-lift) [[Eduard Trulls]](https://etrulls.github.io/) (Image Matching / Feature Detection)
README
# LIFT: Learned Invariant Feature Points
This software is a Python implementation of the LIFT feature point presented in [1].
[1] K. M. Yi, E. Trulls, V. Lepetit, and P. Fua. "LIFT: Learned Invariant Feature Transform", European Conference on Computer Vision (ECCV), 2016.
This software is patented and is strictly for academic purposes only. For other purposes, please contact us. When using this software, please cite [1].
Contact:
Kwang Moo Yi : kwang_dot_yi_at_epfl_dot_ch
Eduard Trulls : eduard_dot_trulls_at_epfl_dot_ch
## Requirements
* OpenCV 3
And the following python requirements:
* Theano
* Lasagne (Dev)
* numpy
* scipy
* flufl.lock
* parse
* h5py
which can be installed with
```bash
pip install -r requirements.txt
```
## Usage
Build the shared library by
```bash
cd c-code/build
cmake ..
make
```
To run the test program simply
```bash
./run.sh
```
## Note
This model was trained with SfM data (Piccadilly Circus dataset), which does not have strong rotation changes. Newer models work better in this case, which will be released soon. In the meantime, you can also use the models in the [learn-orientation](http://github.com/cvlab-epfl/learn-orientation), [benchmark-orientation](http://github.com/cvlab-epfl/benchmark-orientation).