About
Hello! I am currently an undergraduate student at the School of Geospatial Engineering and Science, Sun Yat-sen University, and a Research Assistant at Tsinghua Shenzhen International Graduate School, Tsinghua University. Starting in 2027, I will pursue my Ph.D. at Tsinghua Shenzhen International Graduate School under the supervision of Associate Professor Weijia Li.
My research interests include generative AI, spatial intelligence, and remote sensing with AI. I am passionate about developing foundation model-based approaches for satellite imagery understanding and geospatial analysis.
Selected Publications
View All →One Query, Many Scales: Sparse Mixture-of-Experts for Efficient Hierarchical Cross-View Geo-Localization
Ruijie Fan, Junyan Ye, Qi Zhu, Weijia Li†
arXiv preprint arXiv:2608.01060
A sparse multi-scale dual encoder with probabilistic coarse-to-fine search, introduced together with the VIGOR-M benchmark.
EP-BEV+: A Robust Cross-View Geolocalization Network via Panoramic–Feature BEV Collaboration
Ruijie Fan, Leyan Ou, Junyan Ye, Weijia Li†
June 2026
A cross-view geolocalization study currently under review; further details will be shared after public release.
SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors
Ruijie Fan, Junyan Ye, Huan Chen, Zilong Huang, Xiaolei Wang, Weijia Li
arXiv preprint arXiv:2511.18264
A zero-shot satellite video tracker combining SAM2, Kalman-filter motion constraints, and a state machine for robust tracking under occlusion.
A Raster-Based Method for Building Simplification Considering Shape and Texture Features Based on Remote Sensing Images
Ruijie Fan, Yilang Shen
Geo-spatial Information Science
A superpixel-based approach for building simplification and texturing in remote sensing imagery, enhancing map generalization quality.
News
Our paper GeoMoE is available on arXiv, with code, a project page, and the VIGOR-M dataset
Our paper EP-BEV+ was submitted for review
Joined Tsinghua Shenzhen International Graduate School as a Research Assistant, working with Weijia Li
Started as a Quantitative Intern at RUBY ZHANG PTE. LTD.
Our paper SatSAM2 is available on arXiv
Our paper on raster-based building simplification was published in Geo-spatial Information Science
Awarded the National Scholarship for the second consecutive year
Awarded the National Scholarship for the first time