Lecturer
Huazhong University of Science and Technology (HUST)
China
Email: kxian[at]hust[dot]edu[dot]cn
I am now a Lecturer at HUST. Before that, I was a research fellow at the Nanyang Technological University, working with Prof. Guosheng Lin .
I got my Ph.D. degree and B.Sc. degree at the Huazhong University of Science and Technology, China, supervised by Prof. Zhiguo Cao.
From Aug. 2016 to Sep. 2017, I was a visiting student in Prof.Chunhua Shen's group at the University of Adelaide, Australia.
From Mar. 2019 to Jun. 2019, I was an intern at Adobe Research, working with Dr. Jianming Zhang, Dr. Oliver Wang, Dr. Long Mai, and Dr. Zhe Lin.
Dec. 2023: One paper about robust monocular depth estimation is accepted by IJCV.
Dec. 2023: One paper about motion prediction is accepted at AAAI 2024.
Aug. 2023: One paper about robust video depth estimation is accepted by T-MM. Please refer to our project homepage for details.
Jul. 2023: Three papers are accepted at MM 2023.
Jul. 2023: One paper about video depth estimation is accepted at ICCV 2023.
Jun. 2023: Our team is the Winner of the track 'Bokeh Effect Transformation' at NITRE 2023 (CVPR 2023).
Mar. 2023: One paper about 3D cinemagraphy is accepted at CVPR 2023. Please refer to our project homepage for details.
Sep. 2022: One paper about NeRF is accepted as an ORAL at ACCV 2022.
Jul. 2022: One paper about bokeh rendering is accepted at ECCV 2022. Please refer to our project homepage for details.
Jun. 2022: One paper about video depth estimation is accepted at MM 2022.
Mar. 2022: One paper about bokeh rendering is accepted as an ORAL at CVPR 2022 . Please refer to our project homepage for details.
Feb. 2021: One paper about image cropping is accepted at CVPR 2021 .
Sep. 2020: One paper about talking head animation is accepted at ACCV 2020 .
Aug. 2020: Our team won the 2nd place of the track 'single image depth prediction' at RVC 2020 (ECCV 2020).
Aug. 2020: Our team won the 2nd place of the track 'rendering realistic bokeh' at AIM 2020 (ECCV 2020).
Jul. 2020: One paper about depth completion is accepted at ECCV 2020 .
Feb. 2020: One paper about monocular depth estimation is accepted at CVPR 2020 .
Dec. 2019: One paper is accepted by T-PAMI.
Oct. 2019: One paper is accepted by T-IP.
May. 2019: Three papers are accepted at ICIP 2019.
Mar. 2019: I will be a research intern at Adobe Research in San Jose, USA.
Sep. 21, 2018: One paper is accepted as an ORAL at ACCV 2018 .
Jun. 1, 2018: The 2nd place in the task of Single Image Depth Prediction in the Robust Vision Challenge 2018 ( CVPR 2018).
Feb. 28, 2018: One paper is accepted at CVPR 2018 .
Sep. 02, 2017: One paper is accepted as a SPOTLIGHT at 3DV 2017 .
Jul. 17, 2017: One paper is accepted at ICCV 2017 .
Conference papers:
3D Cinemagraphy from a Single Image
Xingyi Li, Zhiguo Cao, Huiqiang Sun, Jianming Zhang, Ke Xian*, and Guosheng Lin (* Corresponding author)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada.
[Project]
BokehMe: When Neural Rendering Meets Classical Rendering
Juewen Peng, Zhiguo Cao, Xianrui Luo, Hao Lu, Ke Xian*, and Jianming Zhang (* Corresponding author)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA.
[Project](Oral)
MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
Juewen Peng, Jianming Zhang, Xianrui Luo, Hao Lu, Ke Xian*, and Zhiguo Cao (* Corresponding author)
European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel.
[Project]
Composing Photos Like a Photographer
Chaoyi Hong, Shuaiyuan Du, Ke Xian, Hao Lu, Zhiguo Cao, and Weicai Zhong
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), Online.
CPTNet: Cascade Pose Transform Network for Single Image Talking Head Animation
Jiale Zhang, Ke Xian, Chengxin Liu, Yinpeng Chen, Zhiguo Cao, and Weicai Zhong
15th Asian Conference on Computer Vision (ACCV) (ACCV 2020), Kyoto, Japan.
Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction
Xin Xiong, Haipeng Xiong, Ke Xian, Chen Zhao, Zhiguo Cao, and Xin Li
16th European Conference on Computer Vision (ECCV) (ECCV 2020), Glasgow, UK.
Structure-Guided Ranking Loss for Single Image Depth Prediction
Ke Xian, Jianming Zhang, Oliver Wang, Long Mai, Zhe Lin, and Zhiguo Cao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA.
[Project]
Deep Attention-based Classification Network for Robust Depth Prediction
Ruibo Li*, Ke Xian*, Chunhua Shen, Zhiguo Cao, Hao Lu, and Lingxiao Hang (* Equal contributions)
14th Asian Conference on Computer Vision (ACCV) (ACCV 2018), Perth, Australia.
[Arxiv](Oral)
Monocular Relative Depth Perception with Web Stereo Data Supervision
Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li and Zhenbo Luo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA.
[Project]
Performance Evaluation of 3D Correspondence Grouping Algorithms
Jiaqi Yang, Ke Xian, Yang Xiao and Zhiguo Cao
IEEE International Conference on 3D Vision (3DV 2017), Qingdao, China.
[pdf] (Spotlight oral)
Journal papers:
Towards Robust Monocular Depth Estimation: A New Baseline and Benchmark
Ke Xian, Zhiguo Cao, Chunhua Shen, and Guosheng Lin
International Journal of Computer Vision (IJCV), 2023.
ViTA: Video Transformer Adaptor for Robust Video Depth Estimation
Ke Xian, Juewen Peng, Zhiguo Cao, Jianming Zhang, and Guosheng Lin
IEEE Transactions on Multimedia (T-MM), 2023. [code ]
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching
Jiaqi Yang, Ke Xian, Peng Wang, and Yanning Zhang
IEEE Transactions on Image Processing (T-PAMI), 2020.
Image Feature Correspondence Selection: a Comparative Study and a New Contribution
Chen Zhao, Zhiguo Cao, Jiaqi Yang, Ke Xian*, and Xin Li(* Corresponding author)
IEEE Transactions on Image Processing (T-IP), 2020.
Reviewer of TPAMI, TIP, TCSVT, TGRS, Information Sciences, ISPRS Journal of Photogrammetry and Remote Sensing
Reviewer of CVPR2022/2023/2024, ICCV2023, ACCV2020/2022, AAAI2023/2024