Research Profile
Research Experience
Multi-view 3D Reconstruction under Challenging Remote Sensing Observations
Research on image enhancement and multi-view 3D reconstruction from noisy and incomplete observations.
- Motion Estimation and Detection: Modelled non-stationary time series and developed nonlinear parameter-estimation methods for weak-target detection under low-SNR conditions.
- Remote Sensing: Developed physics-aware and learning-based methods for remote sensing image reconstruction under low-SNR, sparse-sampling, and complex-motion conditions.
- Image Enhancement: Developed self-supervised approaches for image enhancement and structure preservation.
- 3D Reconstruction: Investigated multi-view fusion and NeRF/3DGS-based methods for high-fidelity 3D reconstruction.
UAV-Based Urban Remote Sensing and 3D Reconstruction
Developed UAV-based remote sensing and 3D reconstruction methods for complex urban environments.
- Data Acquisition: Participated in 40+ UAV sorties at altitudes of 170–260 m for urban sensing and data collection.
- Motion Estimation: Developed physics-based motion estimation methods for low-SNR and complex-motion observations.
- High-Resolution Imaging: Applied physics-aware methods, achieving meter-level high-resolution imaging under low-SNR and complex-motion conditions.
- 3D Reconstruction: Developed multi-view 3D reconstruction methods, achieving sub-meter reconstruction accuracy.
Multi-view 3D Sensing and Reconstruction of Non-Cooperative Targets
Research on image enhancement and multi-view 3D reconstruction under complex-motion and low-SNR conditions.
- Target Detection and Estimation: Developed parametric target detection and motion-parameter estimation methods for robust weak-target sensing under low-SNR conditions.
- Image Enhancement: Developed self-supervised enhancement methods, achieving 10–15 dB SNR improvement.
- 3D Sensing: Developed NeRF/3DGS-based methods, achieving over 60% improvement in 3D reconstruction accuracy.
- Real-world Validation: Conducted 100+ experiments and processed TB-scale sensor data for algorithm development and validation.
Self-Supervised Reconstruction and Efficient Multimodal Learning
Research on time-series imputation and efficient multimodal learning for incomplete and long-horizon observations.
- Self-Supervised Reconstruction: Developed self-supervised methods for reconstructing incomplete spatiotemporal observations and physics-aware sparse imaging with up to 80% missing measurements.
- 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 time-series 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
An Adaptive 3-D Reconstruction Method for Targets Based on Multi-view Self-supervised Framework under Low SNR
IEEE Transactions on Geoscience and Remote Sensing | First Author
Under Review
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
Multi-Dimensional Spread Target Detection with Across Range-Doppler Unit Phenomenon Based on Generalized Radon-Fourier Transform
Remote Sensing | First Author
Published
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
-
3D Methods
- Multi-view reconstruction
- Sparse-view reconstruction
- NeRF
- 3D Gaussian Splatting (3DGS)
-
Remote Sensing & Image Processing
- Radar imaging
- UAV remote sensing
- Image enhancement
- Target detection and parameter estimation
-
Learning Methods
- Self-supervised learning
- Transformer
- Diffusion models
- Multimodal learning
-
Programming & Experimental Skills
- Python / PyTorch
- MATLAB
- Large-scale real-world sensor data processing
- UAV-based data acquisition and experimental validation
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 over 1,000 participants across universities, companies, and public events.
