Guangkai Xu 徐光锴

Ph.D. Candidate

State Key Lab of CAD & CG, Zhejiang University

Email: guangkai.xu@gmail.com
            guangkai.xu@zju.edu.cn
Google Scholar: Google Scholar Link
Github: https://github.com/guangkaixu
Wechat: Grank_Xu (Discussions and cooperations are welcomed!)

Guangkai Xu

Biography

I'm currently a third-year Ph.D. student of the College of Computer Science and Technology at Zhejiang University, advised by Prof. Chunhua Shen and Hao Chen. Before that, I received my M.S. degree from the Department of Automation, University of Science and Technology of China (USTC) in 2023, where I was a member of USTC-BIVLab, advised by Prof. Feng Zhao, and my B.E. degree from the University of Electronic Science and Technology of China (UESTC) in 2020.

My research interests include Embodied AI with VLMs, MLLMs, and Visual Perception.

Experience

Awards

Publications

* indicates equal contribution (co-first authors). † indicates corresponding author.

♠ (Co-) First author Papers

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, Chunhua Shen†
International Conference on Learning Representations (ICLR), 2025
[PDF] [Code]
FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models
Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen†, Kai Cheng, Feng Zhao
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
[PDF] [Code] [Homepage]
DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-based Dense Incident Map Generation
Xiankang He*, Guangkai Xu*, Bo Zhang, Hao Chen, Ying Cui, Dongyan Guo
AAAI Conference on Artificial Intelligence (Oral), 2025
[PDF] [Code]
Towards Domain-Agnostic Depth Completion
Guangkai Xu, Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Simon Chen, Jia-Wang Bian
Machine Intelligence Research, 2024
[PDF]
Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth
Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen†, Kai Cheng, Feng Wu, Feng Zhao
arXiv preprint arXiv:2202.01470, 2022
[PDF]

♠ Co-author Papers

POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
Songyan Zhang, Yongtao Ge, Jinyuan Tian, Guangkai Xu, Hao Chen, Chen Lv, Chunhua Shen†
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
[PDF] [Code]
Generative video matting
Yongtao Ge, Kangyang Xie, Guangkai Xu, Li Ke, Mingyu Liu, Longtao Huang, Hui Xue, Hao Chen, Chunhua Shen†
Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Papers, 2025
[PDF]
Unleashing the potential of the diffusion model in few-shot semantic segmentation
Muzhi Zhu, Yang Liu, Zekai Luo, Chenchen Jing, Hao Chen, Guangkai Xu, Xinlong Wang, Chunhua Shen†
Neural Information Processing Systems (NeurIPS), 2024
[PDF] [Code]
Improving neural indoor surface reconstruction with mask-guided adaptive consistency constraints
Xinyi Yu, Liqin Lu, Jintao Rong, Guangkai Xu, Linlin Ou
IEEE International Conference on Robotics and Automation (ICRA), 2024
[PDF]
The second monocular depth estimation challenge
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
[PDF] [Homepage]
Geobench: Benchmarking and analyzing monocular geometry estimation models
Yongtao Ge, Guangkai Xu, Zhiyue Zhao, Libo Sun, Zheng Huang, Yanlong Sun, Hao Chen, Chunhua Shen†
arXiv preprint arXiv:2406.12671, 2024
[PDF]
Exploiting correspondences with all-pairs correlations for multi-view depth estimation
Kai Cheng, Hao Chen, Wei Yin, Guangkai Xu, Xuejin Chen
arXiv preprint arXiv:2205.02481, 2022
[PDF]

Professional Activities

Conference Reviewers

Journal Reviewers