diff --git a/README.md b/README.md
index 66d8947..4e5265b 100644
--- a/README.md
+++ b/README.md
@@ -565,6 +565,8 @@ _Deep Learning Methods_
 <b>Fully Convolutional Refined Auto-Encoding Generative Adversarial Networks for 3D Multi Object Scenes (2017)</b> [[Blog]]
 <p align="center"><img width="50%" src="https://cdn-images-1.medium.com/max/1600/1*NckW2hfgbHhEP3P8Z5ZLjQ.png" /></p>
 
+<b>Human-centric Indoor Scene Synthesis Using Stochastic Grammar (2018, CVPR)</b>[[Paper]](http://web.cs.ucla.edu/~syqi/publications/cvpr2018synthesis/cvpr2018synthesis.pdf) [[Supplementary]](http://web.cs.ucla.edu/~syqi/publications/cvpr2018synthesis/cvpr2018synthesis_supplementary.pdf) [[Code]](https://github.com/SiyuanQi/human-centric-scene-synthesis)
+<p align="center"><img width="50%" src="http://web.cs.ucla.edu/~syqi/publications/thumbnails/cvpr2018synthesis.gif" /></p>
 
 <a name="scene_understanding" />