From dacbff4046ab55b5244cc14e151ac677473c4eb7 Mon Sep 17 00:00:00 2001
From: Erik Wijmans <ewijmans2@gmail.com>
Date: Thu, 15 Nov 2018 18:15:09 -0500
Subject: [PATCH] Update README.rst

---
 README.rst | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/README.rst b/README.rst
index b004c9c..d40271c 100644
--- a/README.rst
+++ b/README.rst
@@ -1,7 +1,9 @@
 Pointnet2/Pointnet++ PyTorch
-=================
+============================
 
-Implemention of `Pointnet2/Pointnet++ <https://github.com/charlesq34/pointnet2>`_ written in `PyTorch <http://pytorch.org>`_.
+Implemention of Pointnet2/Pointnet++ written in `PyTorch <http://pytorch.org>`_.
+
+Official code release for the paper (in tensorflow): https://github.com/charlesq34/pointnet2
 
 The custom ops used by Pointnet++ are currently **ONLY** supported on the GPU using CUDA.
 
@@ -18,3 +20,24 @@ Two training examples are provided by ``pointnet2/train/train_sem_seg.py`` and `
 
 The scripts expect that you are in the root directory and have that directory added to your ``PYTHONPATH``,
 i.e ``export PYTHONPATH=$(pwd):${PYTHONPATH}``
+
+
+Citation
+--------
+
+::
+
+  @article{pytorchpointnet++,
+        Author = {Erik Wijmans},
+        Title = {Pointnet++ Pytorch},
+        Journal = {https://github.com/erikwijmans/Pointnet2_PyTorch},
+        Year = {2018}
+  }
+
+  @inproceedings{qi2017pointnet++,
+      title={Pointnet++: Deep hierarchical feature learning on point sets in a metric space},
+      author={Qi, Charles Ruizhongtai and Yi, Li and Su, Hao and Guibas, Leonidas J},
+      booktitle={Advances in Neural Information Processing Systems},
+      pages={5099--5108},
+      year={2017}
+  }