Brief Bio

I'm Xinpu, a passionate and self-motivated explorer of 3D vision research. Currently, I'm a Ph.D. student (Jan. 2023 - ) at the National University of Defense Technology (NUDT), supervised by Profs. Zhen Liu, Yulan Guo and Hanyun Wang. I received my Master and B.E. degrees from NUDT in 2022 and 2020, respectively. My research interests focus on 3D Computer Vision, particularly on object detection and point cloud processing.

Publications & Preprints


GCFI-Net: Global-Local Cross-Spatial-Channel Feature Interaction Network for Point Cloud Geometry Compression
Xinjie Wang, Yifan Zhang, Xinpu Liu, Ke Xu, Jianwei Wan, Yulan Guo, Hanyun Wang*
IEEE Transactions on Mobile Computing, 2025.
DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion
Xinpu Liu, Baolin Hou, Hanyun Wang*, Ke Xu, Jianwei Wan, Yulan Guo
IEEE Transactions on Multimedia, 2025.
TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression
Xinjie Wang, Yifan Zhang, Ting Liu, Xinpu Liu, Ke Xu, Jianwei Wan, Yulan Guo, Hanyun Wang*
Conference on Computer Vision and Pattern Recognition, 2025.
Geometric attribute-guided 3D semantic instance reconstruction
Junhui Wan, Xinpu Liu, Lili Chen, Sheng Ao, Peng Zhang*, Yulan Guo
Journal of Image and Graphics, 2023.
Infrared-Visible image feature dynamic selection object detection network
Ke Xu, Xinpu Liu*, Hanyun Wang, Jianwei Wan, Yulan Guo
Journal of Image and Graphics, 2023.
AGFA-Net: Adaptive Global Feature Augmentation Network for Point Cloud Completion
Xinpu Liu*, Yanxin Ma, Ke Xu, Jianwei Wan, Yulan Guo
IEEE Geoscience and Remote Sensing Letters, 2022.
KASiam: Keypoints-Aligned Siamese Network for the Completion of Partial TLS Point Clouds
Xinpu Liu, Yanxin Ma*, Ke Xu, Ling Wang, Jianwei Wan
Remote Sensing, 2022.
Point cloud completion by dynamic transformer with adaptive neighbourhood feature fusion
Xinpu Liu, Guoquan Xu, Ke Xu, Jianwei Wan, Yanxin Ma*
IET Computer Vision, 2022.
Multi-scale Transformer based point cloud completion network
Xinpu Liu, Yanxin Ma*, Ke Xu, Jianwei Wan, Yulan Guo
Journal of Image and Graphics, 2021.
Human Fall Detection Method Using Millimeter-wave Radar Based on RDSNet
Zhian Yuan, Xiaoyu Zhou, Xinpu Liu, Dawei Lu*, Bin Deng, Yanxin Ma
Journal of Radars, 2021.
Teaching Assistance


Lecture: Digital signal processing (Autumn Term, 2024)
Lecture: Digital signal processing (Spring Term, 2023)
Lecture: Digital signal processing (Autumn Term, 2021)
Awards & Honors


2024 | Outstanding Master Thesis Award of NUDT
2023 | Outstanding Paper Award of the Journal of Image and Graphics
2023 | Excellent Master Graduates of NUDT
2023 | Second place in the 4th Aerospace Cup Innovation Competition (Top2 over 227 teams)
2023 | Outstanding Student Award of NUDT
2022 | First-class Scholarship of NUDT
2021 | First place in the 3th Aerospace Cup Innovation Competition (Top1 over 422 teams)
2021 | Qiangjun Scholarship of NUDT
2020 | The 1st Prize in the Graduate Electronic Design Competition of China (Top 2%)
2020 | Outstanding B.E. Dissertation Award of NUDT
2018 | Silver Medal Winner of the University Physics Competition
2018 | Honorable Mention Award of the Interdisciplinary Contest In Modeling (ICM)