Kai Han

韩锴

Postdoc, 2018.04-
Visual Geometry Group (VGG)
Department of Engineering Science
University of Oxford
Parks Road, Oxford, OX1 3PJ
United Kingdom

Email: khan at robots.ox.ac.uk

Google Scholar | GitHub | LinkedIn | Links

I am Postdoc in the Department of Engineering Science at the University of Oxford, working with Prof. Andrew Zisserman and Prof. Andrea Vedaldi. I completed my PhD in Department of Computer Science at The University of Hong Kong under the advisement of Prof. Kenneth K.Y. Wong in 2018. I was a Research Intern at the WILLOW group (INRIA / École Normale Superiéure, Paris, France) working with Prof. Jean Ponce and Prof. Minsu Cho in 2016. Previously, I received my M.Eng. from Harbin Institute of Technology in 2014 and B.Eng. from Harbin Engineering University in 2011.

Research Interests

My interests are centered around Computer Vision. My current research is mainly focused on 3D computer vision, semantic matching, deep learning in computer vision, etc.

Recent Publications

	Guanying Chen, Kai Han, Kwan-Yee K. Wong PS-FCN: A Flexible Learning Framework for Photometric Stereo European Conference on Computer Vision (ECCV), 2018. paper \| project page
	Guanying Chen, Kai Han*, Kwan-Yee K. Wong TOM-Net: Learning Transparent Object Matting from a Single Image* IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (* indicates equal contribution.) Spotlight Presentation paper \| arXiv \| project page
	Kai Han, Kwan-Yee K. Wong, Miaomiao Liu Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction International Journal of Computer Vision (IJCV), 2017. paper \| DOI
	Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce SCNet: Learning Semantic Correspondence International Conference on Computer Vision (ICCV), 2017. paper \| poster \| arXiv \| HAL \| project page
	Kai Han, Kwan-Yee K. Wong, Xiao Tan Single View 3D Reconstruction under an Uncalibrated Camera and an Unknown Mirror Sphere International Conference on 3D Vision (3DV), 2016. paper \| poster
	Kai Han, Kwan-Yee K. Wong, Dirk Schnieders, Miaomiao Liu Mirror Surface Reconstruction Under an Uncalibrated Camera IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. paper \| poster
	Kai Han, Kwan-Yee K. Wong, Miaomiao Liu A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. paper \| poster

Teaching

[2017/18 1st semester]: COMP2396 Object-oriented Programming and Java ~ Teaching Assistant
[2016/17 2nd semester]: COMP3317 Computer Vision ~ Teaching Assistant
[2015/16 1st semester]: COMP3317 Computer Vision ~ Teaching Assistant
[2014/15 1st semester]: COMP3317 Computer Vision ~ Teaching Assistant

Awards and Honors

Outstanding Reviewer, CVPR 2018

	Guanying Chen, Kai Han, Kwan-Yee K. Wong PS-FCN: A Flexible Learning Framework for Photometric Stereo European Conference on Computer Vision (ECCV), 2018. paper \| project page
	Guanying Chen, Kai Han*, Kwan-Yee K. Wong TOM-Net: Learning Transparent Object Matting from a Single Image* IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (* indicates equal contribution.) Spotlight Presentation paper \| arXiv \| project page
	Kai Han, Kwan-Yee K. Wong, Miaomiao Liu Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction International Journal of Computer Vision (IJCV), 2017. paper \| DOI
	Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce SCNet: Learning Semantic Correspondence International Conference on Computer Vision (ICCV), 2017. paper \| poster \| arXiv \| HAL \| project page
	Kai Han, Kwan-Yee K. Wong, Xiao Tan Single View 3D Reconstruction under an Uncalibrated Camera and an Unknown Mirror Sphere International Conference on 3D Vision (3DV), 2016. paper \| poster
	Kai Han, Kwan-Yee K. Wong, Dirk Schnieders, Miaomiao Liu Mirror Surface Reconstruction Under an Uncalibrated Camera IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. paper \| poster
	Kai Han, Kwan-Yee K. Wong, Miaomiao Liu A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. paper \| poster