Image Matching Using Hybrid Graph Neural Networks

PyTorch implementation of Image Keypoint Matching for Graph Neural Networks. Code based on DGMC. To run the aglorithm presented in the paper use:

$ cd examples/
$ python pascal.py
$ python willow.py
$ python pascal_pf.py

The unmodified scripts use the basline DGMC algorithm.

Requirements

$ python setup.py install

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
build/lib/dgmc		build/lib/dgmc
data/PascalVOC		data/PascalVOC
dgmc		dgmc
dist		dist
docs		docs
examples		examples
figures		figures
test		test
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
README.md		README.md
fixed_plot.png		fixed_plot.png
names0.p		names0.p
names1.p		names1.p
names2.p		names2.p
names3.p		names3.p
names4.p		names4.p
pos0.p		pos0.p
pos1.p		pos1.p
pos2.p		pos2.p
pos3.p		pos3.p
pos4.p		pos4.p
readthedocs.yml		readthedocs.yml
result2.txt		result2.txt
result_gmc.txt		result_gmc.txt
result_pascalpf.txt		result_pascalpf.txt
result_willow.txt		result_willow.txt
setup.cfg		setup.cfg
setup.py		setup.py
testwillow.py		testwillow.py
y0.p		y0.p
y1.p		y1.p
y2.p		y2.p
y3.p		y3.p
y4.p		y4.p