Kai Han

韩 锴

Assistant Professor
Visual Information Laboratory
Department of Computer Science
University of Bristol

    kai.han at bristol.ac.uk / khan at robots.ox.ac.uk
    Merchant Venturers Building
    Woodland Road, Bristol, BS8 1UB, England, United Kingdom

Google Scholar  |   GitHub  |   ORCID  |   DBLP  |   arXiv  |   LinkedIn  |   Twitter

I am a Lecturer (Assistant Professor) in Computer Vision at University of Bristol. Previously, I was a Postdoctoral Researcher in the great Visual Geometry Group (VGG) at the University of Oxford working with Prof. Andrew Zisserman and Prof. Andrea Vedaldi, from 2018 to 2020. Prior to that, I received my Ph.D. degree in Department of Computer Science at The University of Hong Kong advised by Prof. Kenneth K.Y. Wong in 2018. During my Ph.D., I was lucky to work with Prof. Jean Ponce and Prof. Minsu Cho at the WILLOW team of Inria Paris and École Normale Supérieure (ENS) in 2016.

My interests are centered around Computer Vision and Deep Learning, spanning topics like novel category discovery, semi-supervised learning, visual correspondence, 3D reconstruction, image matting, photometric stereo, etc. The broad goal of my research is to achieve principled and comprehensive visual understanding for real applications of artificial intelligent systems.

News

May 2021 One paper about dynamic convolution for semantic scene completion is accepted to TPAMI.
Mar 2021 One paper about long-tailed recognition is accepted to CVPR 2021.
Dec 2020 One paper about mirror surface reconstruction is accepted to IEEE TIP.
Dec 2020 Joined the University of Bristol as a Lecturer.
Sept 2020 One paper about dense correspondence is accepted to NeurIPS 2020.
Jun 2020 One paper about deep photometric stereo is accepted to TPAMI.
Feb 2020 Two papers (about semantic correspondence / 3D semantic scene completion) are accepted to CVPR 2020.
Dec 2019 One paper about novel category discovery is accepted to ICLR 2020.
Jul 2019 One paper about novel category discovery is accepted to ICCV 2019.
Jul 2019 One paper about transparent object matting is accepted to IJCV.
Mar 2019 Two papers (about unsupervised object discovery and matching / uncalibrated photometric stereo) are accepted to CVPR 2019.

Publications

Conference papers

Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, Lei Wang
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
BibTeX  |   PDF  |   arXiv  |   project page  
@inproceedings{wang21contrastive,
 author		= {Peng Wang and Kai Han and Xiu-Shen Wei and Lei Zhang and Lei Wang},
 title   	= {Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification},
 booktitle	= {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year    	= {2021},
}
Xinghui Li, Kai Han, Shuda Li, Victor Prisacariu
Dual-Resolution Correspondence Networks
Conference on Neural Information Processing Systems (NeurIPS), 2020.
BibTeX  |   PDF  |   arXiv  |   supplementary  |   project page  |   code
@inproceedings{li20dualrc,
 author		= {Xinghui Li and Kai Han and Shuda Li and Victor Prisacariu},
 title   	= {Dual-Resolution Correspondence Networks},
 booktitle 	= {Conference on Neural Information Processing Systems (NeurIPS)},
 year    	= {2020},
}
Kai Han*, Sylvestre-Alvise Rebuffi*, Sebastien Ehrhardt*, Andrea Vedaldi, Andrew Zisserman
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
International Conference on Learning Representations (ICLR), 2020. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   OpenReview  |   video  |   project page  |   code
@inproceedings{han20automatically,
 author    = {Kai Han and Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Andrea Vedaldi and Andrew Zisserman},
 title     = {Automatically Discovering and Learning New Visual Categories with Ranking Statistics},
 booktitle = {International Conference on Learning Representations (ICLR)},
 year      = {2020},
}
Shuda Li*, Kai Han*, Theo W. Costain, Henry Howard-Jenkins, Victor Prisacariu
Correspondence Networks with Adaptive Neighbourhood Consensus
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   project page  |   code
@inproceedings{li20correspondence,
 author    = {Shuda Li and Kai Han and Theo W. Costain and Henry Howard-Jenkins and Victor Prisacariu},
 title     = {Correspondence Networks with Adaptive Neighbourhood Consensus},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2020},
}
Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
BibTeX  |   PDF  |   arXiv  |   project page  |   code
@inproceedings{li20anisotropic,
 author    = {Jie Li and Kai Han and Peng Wang and Yu Liu and Xia Yuan},
 title     = {Anisotropic Convolutional Networks for 3D Semantic Scene Completion},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2020},
}
Sylvestre-Alvise Rebuffi*, Sebastien Ehrhardt*, Kai Han*, Andrea Vedaldi, Andrew Zisserman
Semi-Supervised Learning with Scarce Annotations
CVPR Deep Vision Workshop, 2020. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   project page  |   code
@inproceedings{rebuffi20SSL,
 title={Semi-Supervised Learning with Scarce Annotations},
 author={Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Kai Han and  Andrea Vedaldi and Andrew Zisserman},
 booktitle={CVPR Deep Vision Workshop},
 year={2020}
}
Kai Han, Andrea Vedaldi, Andrew Zisserman
Learning to Discover Novel Visual Categories via Deep Transfer Clustering
International Conference on Computer Vision (ICCV), 2019.
BibTeX  |   PDF  |   arXiv  |   supplementary  |   project page  |   code
@inproceedings{han19DTC,
 author    = {Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title     = {Learning to Discover Novel Visual Categories via Deep Transfer Clustering},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2019}
}
Huy V. Vo, Francis Bach, Minsu Cho, Kai Han, Yann LeCun, Patrick Pérez, Jean Ponce
Unsupervised Image Matching and Object Discovery as Optimization
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
BibTeX  |   PDF  |   arXiv  |   code
@inproceedings{vo19unsup,
 title     = {Unsupervised Image Matching and Object Discovery as Optimization},
 author    = {Huy V. Vo and Francis Bach and Minsu Cho and Kai Han and Yann LeCun and Patrick P\'{e}rez and Jean Ponce},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2019}
}
Guanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong
Self-calibrating Deep Photometric Stereo Networks
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Oral presentation
BibTeX  |   PDF  |   arXiv  |   supplementary  |   video  |   poster  |   project page  |   code
@inproceedings{chen19SDPS_Net,
 title     = {Self-calibrating Deep Photometric Stereo Networks},
 author    = {Guanying Chen and Kai Han and Boxin Shi and Yasuyuki Matsushita and Kwan-Yee K. Wong},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2019}
}
Guanying Chen, Kai Han, Kwan-Yee K. Wong
PS-FCN: A Flexible Learning Framework for Photometric Stereo
European Conference on Computer Vision (ECCV), 2018.
BibTeX  |   PDF  |   arXiv  |   video  |   poster  |   project page  |   code
@inproceedings{chen18ps_fcn,
 title     = {PS-FCN: A Flexible Learning Framework for Photometric Stereo},
 author    = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 booktitle = {European Conference on Computer Vision (ECCV)},
 year      = {2018}
}
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
BibTeX  |   PDF  |   arXiv  |   video  |   poster  |   project page  |   code
@inproceedings{chen18tom_net,
 title     = {TOM-Net: Learning Transparent Object Matting from a Single Image},
 author    = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2018}
}
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.
BibTeX  |   PDF  |   arXiv  |   HAL  |   poster  |   project page  |   code
@inproceedings{han17scnet,
 title     = {SCNet: Learning Semantic Correspondence},
 author    = {Kai Han and Rafael S. Rezende and Bumsub Ham and Kwan-Yee K. Wong and Minsu Cho and Cordelia Schmid and Jean Ponce},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2017}
}
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.
BibTeX  |   PDF  |   poster
@inproceedings{han16single,
 author    = {Kai Han and Kwan-Yee K. Wong and Xiao Tan},
 title     = {Single View 3D Reconstruction under an Uncalibrated Camera and an Unknown Mirror Sphere},
 booktitle = {International Conference on 3D Vision (3DV)},
 year      = {2016}
}
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.
BibTeX  |   PDF  |   project page  |   poster  |   code
@inproceedings{han16mirror,
 author    = {Kai Han and Kwan-Yee K. Wong and Dirk Schnieders and Miaomiao Liu},
 title     = {Mirror Surface Reconstruction under an Uncalibrated Camera},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2016}
}
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.
BibTeX  |   PDF  |   poster
@inproceedings{han15afixed,
 author    = {Kai Han and Kwan-Yee K. Wong and Miaomiao Liu},
 title     = {A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2015}
}

Journal papers

Jie Li, Peng Wang, Kai Han, Yu Liu
Anisotropic Convolutional Neural Networks for RGB-D based Semantic Scene Completion
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
BibTeX  |   PDF  |   arXiv  |   DOI  |   project page  |   code
@inproceedings{li21anisotropic,
 author    = {Jie Li and Peng Wang and Kai Han and Yu Liu},
 title     = {Anisotropic Convolutional Neural Networks for RGB-D based Semantic Scene Completion},
 booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year      = {2021},
}
Kai Han, Miaomiao Liu, Dirk Schnieders, Kwan-Yee K. Wong
Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
IEEE Transactions on Image Processing (TIP), 2021.
BibTeX   |   PDF  |   arXiv  |   DOI  |   supplementary  |   project page  |   code
@article{han21fixed,
 title   = {Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera},
 author  = {Kai Han and Miaomiao Liu and Dirk Schnieders and Kwan-Yee K. Wong},
 journal = {IEEE Transactions on Image Processing (TIP)},
 year    = {2021}
}
Guanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong
Deep Photometric Stereo for Non-Lambertian Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
BibTeX  |   PDF  |   arXiv  |   DOI  |   supplementary  |   project page  |   code
@article{chen20deepps,
 title   = {Deep Photometric Stereo for Non-Lambertian Surfaces},
 author  = {Guanying Chen and Kai Han and Boxin Shi and Yasuyuki Matsushita and Kwan-Yee K. Wong},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year    = {2020}
}
Guanying Chen*, Kai Han*, Kwan-Yee K. Wong
Learning Transparent Object Matting
International Journal of Computer Vision (IJCV), 2019. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   DOI  |   supplementary  |   project page  |   code
@article{chen19LTOM,
 title   = {Learning Transparent Object Matting},
 author  = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 journal = {International Journal of Computer Vision (IJCV)},
 year    = {2019}
}
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), 2018.
BibTeX  |   PDF  |   arXiv  |   DOI
@article{han18dense,
 title   = {Dense Reconstruction of Transparent Objects by Altering Incident Light Paths through Refraction},
 author  = {Kai Han and Kwan-Yee K. Wong and Miaomiao Liu},
 journal = {International Journal of Computer Vision (IJCV)},
 year    = {2018}
}

Preprints

Xuhui Jia, Kai Han, Yukun Zhu, Bradley Green
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
arXiv preprint, 2021.
BibTeX  |   PDF  |   arXiv  
@article{jia21joint,
 author  = {Xuhui Jia and Kai Han and Yukun Zhu and Bradley Green},
 title   = {Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data},
 journal = {arXiv preprint arXiv:2104.12673},
 year    = {2021}
}
Georgi Tinchev, Shuda Li, Kai Han, David Mitchell, Rigas Kouskouridas
XResolution Correspondence Networks
arXiv preprint, 2020.
BibTeX  |   PDF  |   arXiv  |   project page  |   code
@article{tinchev20xresolution,
 author  = {Georgi Tinchev and Shuda Li and Kai Han and David Mitchell and Rigas Kouskouridas},
 title   = {XResolution Correspondence Networks},
 journal = {arXiv preprint arXiv:2012.09842},
 year    = {2020}
}
Sylvestre-Alvise Rebuffi*, Sebastien Ehrhardt*, Kai Han*, Andrea Vedaldi, Andrew Zisserman
LSD-C: Linearly Separable Deep Clusters
arXiv preprint, 2020. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   code
@article{rebuffi20lsdc,
 author  = {Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title   = {LSD-C: Linearly Separable Deep Clusters},
 journal = {arXiv preprint arXiv:2006.10039},
 year    = {2020}
}
Yuda Qiu*, Zhangyang Xiong*, Kai Han, Zhongyuan Wang, Zixiang Xiong, Xiaoguang Han
Learning Inverse Rendering of Faces from Real-world Videos
arXiv preprint, 2020. (* indicates equal contribution.)
BibTeX  |   PDF  |   arXiv  |   code
@article{qiu20learning,
 author  = {Yuda Qiu and Zhangyang Xiong and Kai Han and Zhongyuan Wang and Zixiang Xiong and Xiaoguang Han},
 title   = {Learning Inverse Rendering of Faces from Real-world Videos},
 journal = {arXiv preprint arXiv:2003.12047},
 year    = {2020},
}

PhD Dissertation

Kai Han
Single view reconstruction of transparent, mirror and diffuse surfaces
The University of Hong Kong, Pokfulam, Hong Kong, 2018.
BibTeX  |   PDF  |   HKU Theses Online
@phdthesis{han18phd,
 author = {Kai Han},
 title  = {Single view reconstruction of transparent, mirror and diffuse surfaces},
 school = {Department of Computer Science, The University of Hong Kong},
 year   = {2018}
}

Awards and Honors

Professional Activities

Teaching

Copyright © Kai Han. All Rights Reserved.