Research Profile
Research Experience
3D Reconstruction from Sparse and Noisy Multi-view Observations
Developed multi-view reconstruction methods for sparse and noisy observations.
- Multi-view Modelling: Modelled geometric relationships between multi-view observations and 3D structures to support reconstruction from limited viewpoints.
- Image Enhancement: Developed multi-view self-supervised methods to suppress noise while preserving geometry-consistent structures without requiring clean reference images.
- 3D Reconstruction: Investigated multi-view fusion and NeRF/3DGS-based methods for high-fidelity 3D reconstruction.
- Parametric 3D Reconstruction: Investigated parametric 3D reconstruction under low-SNR and complex-motion conditions.
Multi-view 3D Reconstruction of Space Targets
Research on 3D reconstruction of non-cooperative targets from long-range, low-SNR multi-view observations.
- Motion–Geometry Joint Estimation: Modelled low-SNR observations by jointly considering target motion and scatterer distribution, enabling simultaneous estimation of motion parameters and 3D structure.
- 3D Sensing: Investigated sparse-view methods for lunar-surface 3D reconstruction.
- Image Enhancement: Developed self-supervised enhancement methods, achieving 10–15 dB SNR improvement.
- Real-world Validation: Conducted 100+ experiments and processed TB-scale sensor data for algorithm validation.
UAV-Based Urban Sensing and 3D Reconstruction
Developed UAV-based sensing and 3D reconstruction methods for complex urban environments.
- Multi-view Acquisition: Participated in 40+ UAV sorties at 170–260 m for urban sensing and data collection.
- Motion Estimation: Developed parametric motion-estimation methods for low-SNR and complex-motion conditions.
- Urban Sensing Imaging: Applied physics-aware methods for high-resolution imaging under low SNR.
- 3D Reconstruction: Developed multi-view 3D reconstruction methods, achieving sub-meter reconstruction accuracy.
Self-Supervised Reconstruction and Efficient Multimodal Learning
Research on self-supervised reconstruction and multimodal learning for incomplete and long-horizon observations.
- Missing-Data Reconstruction: Developed self-supervised methods for reconstructing missing spatiotemporal echoes.
- Sparse Imaging: Designed physics-aware methods for high-resolution imaging with up to an 80% echo missing rate.
- Multimodal Learning: Investigated VLM-based modelling of long-horizon time series by retaining informative temporal segments and removing redundant observations.
- Efficient Representation: Explored attention-guided temporal token selection for efficient multimodal reasoning.
Selected Publications & Patents
A Parametric 3-D ISAR Imaging Method of Celestial Target Under Low SNR
IEEE Transactions on Geoscience and Remote Sensing | co-Author
Published
Multi-Dimensional Spread Target Detection with Across Range-Doppler Unit Phenomenon Based on Generalized Radon-Fourier Transform
Remote Sensing | First Author
Published
Scattering-Aware Multi-View Masked Networks for Self-Supervised Radar Denoising
IEEE Transactions on Geoscience and Remote Sensing | First Author
Under Review
A Self-supervised Radar Sparse Imaging Method via Physics-Aware Imputation Network
IEEE Transactions on Aerospace and Electronic Systems | First Author
Under Review
An Adaptive 3-D Reconstruction Method for Targets Based on Multi-view Self-supervised Framework under Low SNR
IEEE Transactions on Aerospace and Electronic Systems | First Author
Under Review
Method for Multi-view 3D Sensing under Low SNR
Chinese Invention Patent | First Student Inventor
Granted
Sensor Denoising Method Based on Self-Supervised Learning
Chinese Invention Patent | First Student Inventor
Granted
Self-Supervised Image Denoising Method Based on an Adaptive Masking Strategy
Chinese Invention Patent | First Student Inventor
Patent Application
Image Reconstruction Method Based on a Self-Supervised Inpainting Network
Chinese Invention Patent | First Student Inventor
Patent ApplicationEducation
Relevant coursework: Signals and Systems, Digital Signal Processing, Communication Principles.
Technical Skills
-
Reconstruction & Representation
- Multi-view reconstruction
- Sparse-view reconstruction
- NeRF / 3D Gaussian Splatting (3DGS)
- Geometry-aware reconstruction
-
Learning Methods
- Self-supervised learning
- Transformer
- Diffusion models
- Multimodal / VLM-based learning
-
Sensing & Imaging
- Low-SNR sensing
- Image enhancement
- Target detection
- Parameter estimation
-
Languages, Frameworks & Tools
- Python / PyTorch
- MATLAB
- C++
- COLMAP / MeshLab / CST
Honors & Awards
China Scholarship Council Scholarship
Funded visiting PhD research at the University of Auckland.
Beijing Outstanding Graduate
Recognized for outstanding academic achievement and comprehensive performance.
First-Class Scholarships
Received multiple municipal- and university-level scholarships for academic excellence.
National Level-II Athlete Standard in Marathon Running
Long-term endurance athlete with 20+ races completed.
AHA / Red Cross First Aid Instructor
Certified first aid instructor with experience supporting large-scale events.
Outstanding Student Leader (3 Awards)
Recognized three times for leadership, teamwork, and contributions to student activities.
Leadership & Activities
Summer Teaching Volunteer Program, China
- Initiated and organized educational outreach programs in rural areas, coordinating volunteer recruitment, curriculum design, school engagement, and team management.
American Heart Association & Beijing Red Cross
- Delivered CPR and first-aid training to more than 1,000 participants across universities, companies, and public events.
