I am a Postdoc in Autonomous Vision Group, a part of the MPI for Intelligent Systems and the University of Tübingen leading by Prof. Andreas Geiger. I received my Ph.D. in Control Science and Engineering from Zhejiang University in June 2018, where I worked with Prof. Yong Liu. Before that, I received the B.S. degree from Xi’an Jiaotong University in Automation.

My research interests include computer vision and deep learning, in especially their applications for semantic and geometric scene understanding in 3D. Currently, I am working on 3D reconstruction and simultaneously 2D and 3D scene understanding.

Contact: yiyi [dot] liao [at] tue [dot] mpg [dot] de
Address: Max-Planck-Ring 4, 72076 Tübingen, Germany

Projects


Deep Marching Cubes: Learning Explicit Surface Representations

Yiyi Liao, Simon Donné, Andreas Geiger
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[Paper] [Code] [Website]



On the Integration of Optical Flow and Action Recognition

Laura Sevilla-Lara, Yiyi Liao, Fatma Güney, Varun Jampani, Andreas Geiger, Michael J. Black
German Conference on Pattern Recognition (GCPR), 2018
[Paper]



Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation

Yiyi Liao, Lichao Huang, Yue Wang, Sarath Kodagoda, Yinan Yu, Yong Liu
IEEE Conference on Robotics and Automation (ICRA), 2017
[Paper]



Graph Regularized Auto-Encoders for Image Representation

Yiyi Liao, Yue Wang, Yong Liu
IEEE Transactions on Image Processing (TIP), 2017
[Paper]



Place classification with a graph regularized deep neural network

Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong Liu
IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2017
[Paper]



Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks

Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong Liu
IEEE Conference on Robotics and Automation (ICRA), 2016
[Paper]