Hao Zhao got his Ph.D. and bachelor degrees from the Electronic Engineering department of Tsinghua University. He was a research scientist at Intel Labs China. He was a joint postdoc affiliated to Peking University. His research focuses on geometric and cognitive scene understanding and its applications in robotics. He has published about 30 top-tier papers on computer vision and robotics venues (CVPR,ICCV,ECCV,IJCV,CVIU,ISPRS,T-IP,T-MM,NeurIPS,ICLR,RA-L,ICRA,IROS). He was also the founder and leader of THU’s largest robotics club Skyworks, launching over 10 high-tech startups. He was the winner of many prestigious academic challenges like LSUN, Holistic3D, LID, etc.

Selected Publications：

[1] Wu, X., Zhao, H., Cao, Y., Li, S., & Zha, H. SC-wLS: Towards Interpretable Feed-forward Camera Re-localization, ECCV 2022

[2] Zhao, H., Lu, M., Yao, A., Guo, Y., Chen, Y., & Zhang, L. Pointly-supervised scene parsing with uncertainty mixture, CVIU 2020

[3] Zhao, H., Lu, M., Yao, A., Chen, Y., & Zhang, L. Learning to Draw Sight Lines, IJCV 2019

[4] Zhang, J., Zhao, H., Yao, A., Chen, Y., Zhang, L., & Liao, H. Efficient semantic scene completion network with spatial group convolution, ECCV 2018

[5] Zhao, H., Lu, M., Yao, A., Guo, Y., Chen, Y., & Zhang, L. Physics inspired optimization on semantic transfer features: An alternative method for room layout estimation, CVPR 2017