Beilei Cui

Room 424, Ho Sin-Hang Engineering Building

CUHK, Shatin, N.T., Hong Kong, 999077

Email: beileicui AT link.cuhk.edu.hk

I am currently a Ph.D student at Robotics, Embodied AI, Navigation in vivo Lab (REN Lab) of the Department of Electronic Engineering, The Chinese University of Hong Kong, supervised by Prof. Hongliang Ren. Previously, I received my B.Eng. degree in 2021 in School of Information and Communication Engineering, University of Electronic Science and Technology of China, advised by Prof. Zhizhong Fu. I also studied at Department of Electrical and Electronic Engineering in Imperial College London and received my M.Sc degree in 2022 advised by Dr. Javier Barria.

My research interests include artificial intelligent applications in medical image analysis, robotic perception and robotic navigation. I am recently working on self-supervised monocular depth estimation, 3D reconstruction, NeRF, noisy label learning.

I am always passionate about discussion or potential cooperation opportunities so feel free to contact me via email if have related inquiries! REN Lab is also open for research interns, don’t hesitate to contact me if you are interested. Specifically, Student helper programme are available for CUHK undergraduate & MSc students.

news

Feb 20, 2026	One paper, TR2M on depth transformation with language assistance, is accepted by CVPR 2026!
Jan 31, 2026	One paper, EndoDDC on endoscopic depth completion, is accepted by ICRA 2026!
Jun 18, 2025	TR2M on transferring relative depth to metric depth is online.
Jun 18, 2025	Two papers, Endo-4DGX and SurgOVGS, are accepted by MICCAI 2025.
Mar 21, 2025	Endo3DAC on surgical monocular depth estimation and 3D reconstruction is online.

selected publications

CVPR

TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Scale-Oriented Contrast

Beilei Cui^*, Yiming Huang^*, Long Bai, and Hongliang Ren^†

In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2026

arXiv Bib Code

@inproceedings{cui2025tr2m,
  title = {TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Scale-Oriented Contrast},
  author = {Cui, Beilei and Huang, Yiming and Bai, Long and Ren, Hongliang},
  booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
  pages = {100--100},
  year = {2026},
  publisher = {IEEE},
}

Nature Communications

Motor-free telerobotic endomicroscopy for steerable and programmable imaging in complex curved and localized areas

Sishen Yuan^*, Chao Xu^*, Beilei Cui^*, Tinghua Zhang, Baijia Liang, and 2 more authors

Nature Communications, 2024

DOI Bib HTML

@article{yuan2024motor,
  title = {Motor-free telerobotic endomicroscopy for steerable and programmable imaging in complex curved and localized areas},
  author = {Yuan, Sishen and Xu, Chao and Cui, Beilei and Zhang, Tinghua and Liang, Baijia and Yuan, Wu and Ren, Hongliang},
  journal = {Nature Communications},
  volume = {15},
  number = {1},
  pages = {7680},
  year = {2024},
  publisher = {Nature Publishing Group UK London},
  doi = {10.1038/s41467-024-51633-x},
}

MICCAI

EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

Beilei Cui^*, Mobarakol Islam^*, Long Bai^*, An Wang, and Hongliang Ren^†

In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024

Early Accept, top 11%

arXiv Bib HTML Code

@inproceedings{cui2024endodac,
  title = {EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera},
  author = {Cui, Beilei and Islam, Mobarakol and Bai, Long and Wang, An and Ren, Hongliang},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  pages = {90--100},
  year = {2024},
  organization = {Springer},
  note = {Early Accept, top 11%},
}

MICCAI

Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting

Yiming Huang^*, Beilei Cui^*, Long Bai^*, Ziqi Guo, Mengya Xu, and 1 more author

In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024

arXiv Bib HTML Code

@inproceedings{huang2024endo,
  title = {Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting},
  author = {Huang, Yiming and Cui, Beilei and Bai, Long and Guo, Ziqi and Xu, Mengya and Ren, Hongliang},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  pages = {90--100},
  year = {2024},
  organization = {Springer},
}

IPCAI

Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

Beilei Cui^*, Mobarakol Islam^*, Long Bai, and Hongliang Ren^†

In International Journal of Computer Assisted Radiology and Surgery (IJCARS) IPCAI, 2024

Long Oral, Best Paper Awards Shortlist

DOI arXiv Bib HTML Code

@inproceedings{cui2024surgical,
  title = {Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery},
  author = {Cui, Beilei and Islam, Mobarakol and Bai, Long and Ren, Hongliang},
  booktitle = {International Journal of Computer Assisted Radiology and Surgery (IJCARS) IPCAI},
  year = {2024},
  note = {Long Oral, Best Paper Awards Shortlist},
  doi = {10.1007/s11548-024-03083-5},
}

MICCAI

Rectifying Noisy Labels with Sequential Prior: Multi-scale Temporal Feature Affinity Learning for Robust Video Segmentation

Beilei Cui^*, Minqing Zhang^*, Mengya Xu^*, An Wang, Wu Yuan, and 1 more author

In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023

DOI arXiv Bib HTML Code

@inproceedings{cui2023rectifying,
  title = {Rectifying Noisy Labels with Sequential Prior: Multi-scale Temporal Feature Affinity Learning for Robust Video Segmentation},
  author = {Cui, Beilei and Zhang, Minqing and Xu, Mengya and Wang, An and Yuan, Wu and Ren, Hongliang},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  pages = {90--100},
  year = {2023},
  organization = {Springer},
  doi = {10.1007/978-3-031-43996-4_9},
}