This is an implementation of the paper "Deep Learning of Graph Matching", CVPR, 2018. Note: This is not an official implementation.

To run the above code, install the dependecies as listed in environment.yml. The easiest way to do this is to setup a conda environemnt

conda env create -f environment.yml

conda activate dlgm

Then update the parameters in the config_sintel.py script according to your hardware availability and needs.

python main.py --dataset sintel --data_path path/to/sintel/root

Note that only sintel dataset is supported as of now. We are not able to exactly reproduce the results of the paper. But the graph matching layers corresponding to optical flow has been tested for correctness. A primitive implementation of the Bistochastic layer is available but is not tested.

There is lot of scope for improvements with respect to the performance. PR's and discussion in this regard or any general matter on this topic is welcome :)