Ke Xian
Email : kxian[at]hust[dot]edu[dot]cn
I am now a lecturer at the School of Electronic Information and Communications, Huazhong University of Science and Technology. I was a Research Fellow at S-Lab, Nanyang Technological University, working with Prof. Guosheng Lin.

(Google scholar)

I got my Ph.D. degree and B.Sc. degree at the Huazhong University of Science and Technology, supervised by Prof. Zhiguo Cao. From Aug. 2016 to Sep. 2017, I was a visiting student at 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. My research primarily centers on computer vision and computational photography, such as robust depth estimation, neural generation/rendering/editing.

News

  • Nov, 2024: One paper about bokeh rendering is accepted By IEEE T-PAMI.
  • Oct, 2024: I received a new funding supprt from CCF-Zhipu Large Model Innovation Fund (15/136). Thank you CCF-Zhipu.
  • Oct, 2024: One paper about video depth estimation is accepted By IEEE T-PAMI.
  • Sep, 2024: One paper about depth estimation is accepted at NeurIPS 2024.
  • Aug, 2024: I received an NSFC grant to support my research. Thank you NSFC.
  • Jul, 2024: One paper about 3D scene generation is accepted at MM 2024.
  • Mar, 2024: One paper about talking head animation is accepted by IEEE TCSVT.
  • Feb, 2024: Three papers are accepted at CVPR 2024. See you in Seattle!
  • Dec, 2023: One paper about robust monocular depth estimation is accepted by IJCV. Code, model, and data will be released at here.
  • Dec, 2023: One paper about motion prediction is accepted at AAAI 2024.
  • Aug, 2023: One paper about robust video depth estimation is accepted by IEEE TMM. 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.

Publications (Selected)

NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation
Yiran Wang, Min Shi, Jiaqi Li, Chaoyi Hong, Zihao Huang, Juewen Peng, Zhiguo Cao, Jianming Zhang, Ke Xian*, and Guosheng Lin. (*corresponding author)
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024, IF=20.8, [PDF] [code]
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), 2024, IF=19.5, [PDF] [code]
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, IF=7.3, [PDF] [Project]
Neural Video Depth Stabilizer
Yiran Wang, Min Shi, Jiaqi Li, Zihao Huang, Zhiguo Cao, Jianming Zhang, Ke Xian*, and Guosheng Lin. (*corresponding author)
ICCV 2023, [PDF] [Project]
3D Cinemagraphy from a Single Image
Xingyi Li, Zhiguo Cao, Huiqiang Sun, Jianming Zhang, Ke Xian*, and Guosheng Lin. (*corresponding author)
CVPR 2023, [PDF] [Project]
Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image
Liao Shen, Xingyi Li, Huiqiang Sun, Juewen Peng, Ke Xian*, Zhiguo Cao, and Guosheng Lin. (*corresponding author)
ACM MM 2023, [PDF] [Code]
BokehMe: When Neural Rendering Meets Classical Rendering
Juewen Peng, Zhiguo Cao, Xianrui Luo, Hao Lu, Ke Xian*, and Jianming Zhang. (*corresponding author)
CVPR 2022 Oral, [PDF] [Project]
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)
ECCV 2022, [PDF] [Project]
Less is More: Consistent Video Depth Estimation with Masked Frames Modeling
Yiran Wang, Zhiyu Pan, Xingyi Li, Zhiguo Cao, Ke Xian*, and Jianming Zhang. (*corresponding author)
ACM MM 2022, [PDF] [Code]
Structure-Guided Ranking Loss for Single Image Depth Prediction
Ke Xian, Jianming Zhang, Oliver Wang, Long Mai, Zhe Lin, and Zhiguo Cao.
CVPR 2020, [PDF] [Project]
Monocular Relative Depth Perception with Web Stereo Data Supervision
Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li, and Zhenbo Luo.
CVPR 2018, [PDF] [Project]

Professional activities

    Journals

    Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

    Transaction on Image Processing(TIP)

    IEEE Transactions on Circuits and Systems for Video Technology(TCSVT)

    IEEE Transactions on Geoscience and Remote Sensing(TGRS)

    Conferences

    CVPR, ICCV, ECCV, AAAI, MM, etc.

Competitions

  • Winner award in NTIRE 2023 Bokeh Effect Transformation Challenge.
  • Runner-up award in AIM 2020 Challenge on Rendering Realistic Bokeh.
  • Runner-up award in Mobile AI Challenge 2021 on Monocular Depth Estimation.
  • Runner-up award in Robust Vision Challenge 2020 on Monocular Depth Prediction.
  • Runner-up award in Robust Vision Challenge 2018 on Monocular Depth Prediction.
  • Champion in Renesas MCU Car Rally 2012.

Last Updated on 18th Dec, 2023

Published with GitHub Pages