I am a tenure-track research professor in Zhejiang University. Before that, I was a Postdoc in Autonomous Vision Group, a part of the University of Tübingen and the MPI for Intelligent Systems, working with Prof. Andreas Geiger. I received my Ph.D. in Control Science and Engineering from Zhejiang University in 2018 and the B.S. degree from Xi’an Jiaotong University.

My research interest lies in 3D computer vision, including 3D scene understanding, 3D reconstruction, depth estimation and 3D controllable image synthesis.

News

Sep 29, 2021 Two papers (1 oral, 1 poster) are accepted to NeurIPS 2021.
Jun 23, 2021 Our work SMD-Nets was featured on the CVPR Daily and the BEST OF CVPR of Computer Vision News.
Jun 1, 2021 I will be joining Zhejiang University as a tenure-track research professor this September!
May 31, 2021 I will serve as an Area Chair for BMVC 2021.
May 19, 2021 I was acknowledged as Outstanding Reviewer at CVPR 2021.

Projects


KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Yiyi Liao, Jun Xie, Andreas Geiger
[Paper] [Dataset] [Utility scripts] [Annotation Tool]



KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Christian Reiser, Songyou Peng, Yiyi Liao, Andreas Geiger
International Conference on Computer Vision (ICCV), 2021
[Paper] [Code] [Blog]



SMD-Nets: Stereo Mixture Density Networks

Fabio Tosi, Yiyi Liao, Carolin Schmitt, Andreas Geiger
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[Paper] [Code] [Blog] [BEST OF CVPR]



Learning Steering Kernels for Sparse-to-Dense Depth Estimation

Lina Liu, Yiyi Liao*, Yue Wang, Andreas Geiger, Yong Liu (*corresponding author)
IEEE Transactions on Image Processing (TIP), 2021
[Paper]



GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

Katja Schwarz*, Yiyi Liao*, Michael Niemeyer, and Andreas Geiger (*equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), 2020
[Paper] [Code] [Blog]



Towards Unsupervised Learning of Generative models for 3d Controllable Image Synthesis

Yiyi Liao*, Katja Schwarz*, Lars Mescheder, and Andreas Geiger (*equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper] [Code] [Website] [Blog]



Connecting the Dots: Learning Representations for Active Monocular Depth Estimation

Gernot Riegler*, Yiyi Liao*, Simon Donné, Vladlen Koltun, and Andreas Geiger (*equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper] [Code] [Website]



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]