home.md

@@ -16,4 +16,6 @@ to perform global assignments in 3D purely from data, handles
 noisy detections and a varying number of targets, and is easy
 to train. We evaluate our approach on the challenging KITTI
 dataset and show competitive results. Our code is available at
-https://git.uwaterloo.ca/wise-lab/fantrack.
\ No newline at end of file
+https://git.uwaterloo.ca/wise-lab/fantrack.
+
+## Paper: https://arxiv.org/pdf/1905.02843.pdf
\ No newline at end of file