Curriculum Vitae个人简历
LI Kai李锴
PhD candidate working on off-nadir remote sensing, promptable vision models and 3D scene understanding.博士研究生,研究方向为偏移摄影遥感、可提示视觉大模型与三维场景理解。
Open to faculty, postdoctoral, research scientist and algorithm engineer positions from 2026.2026 年起开放教职、博士后、研究科学家与算法工程师岗位机会。
Profile个人简介
Research focus研究方向
Computer Vision · Remote Sensing · Vision-Language Models计算机视觉 · 遥感影像理解 · 视觉语言大模型
Contact联系方式
Beijing, China / Hong Kong SAR中国北京 / 中国香港
WeChat: kaili37
Education教育背景
-
2024 – Present
Ph.D. Candidate in Data Science博士研究生,数据科学
City University of Hong Kong (CityU) · School of Data Science香港城市大学(CityU)· 数据科学学院
- Supervised by Prof. Xiangyu Zhao, Applied Machine Learning Lab (AML).导师:赵翔宇 教授,应用机器学习实验室(AML)。
- Research on vision-language models and 3D scene understanding.研究方向:视觉语言大模型与三维场景理解。
-
2021 – Present
Ph.D. Candidate (direct entry), Cartography & Signal and Information Processing博士研究生(本科直博),地图学与信号与信息处理
University of Chinese Academy of Sciences (UCAS) · Aerospace Information Research Institute中国科学院大学(UCAS)· 空天信息创新研究院
- Supervised by Prof. Zhongming Zhao and Prof. Yu Meng.导师:赵忠明 教授、孟瑜 教授。
- Research on building extraction from off-nadir remote sensing imagery.研究方向:偏移摄影视角下的遥感建筑物提取。
-
Until 2021
B.Eng. in Space Information and Digital Technology工学学士,空间信息与数字技术
University of Electronic Science and Technology of China (UESTC)电子科技大学(UESTC)
- Ranked 2nd in the major; recommended for direct PhD admission to UCAS.专业排名第 2;获推荐免试直接攻读博士学位(直博)。
Experience研究与实习经历
-
2025.10 – Present
Research Intern, Omni Research Team研究实习生,Omni 研究团队
Tencent腾讯
- Second collaboration with the team; research on multimodal large models.第二次加入该团队,从事多模态大模型相关研究。
-
2021 – Present
Research Assistant, Off-Nadir Remote Sensing Group研究助理,偏移摄影遥感方向
Aerospace Information Research Institute, Chinese Academy of Sciences中国科学院空天信息创新研究院
- Built the Offset Token research line: OBM, PolyFootNet, DragOSM, ObliCity/DragRoof, LODEOT.构建偏移量词元研究主线:OBM、PolyFootNet、DragOSM、ObliCity/DragRoof、LODEOT。
Publications发表论文
-
Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model
-
PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images
-
DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels
-
ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correction
-
Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs
-
SAMPolyBuild: Adapting the Segment Anything Model for polygonal building extraction
-
A Wordnet-Based Geospatial Web Services Search Method Supporting Quality of Service Constraints
Awards & Honours获奖与荣誉
-
2025
Nominee, IEEE Excellence in Technical Communication Student Prize AwardIEEE Excellence in Technical Communication Student Prize Award 提名
IEEE Geoscience and Remote Sensing Society (GRSS) — the only Chinese nominee of the yearIEEE 地球科学与遥感学会(GRSS)— 年度唯一华人被提名者
-
2025
3MT Competition Final Round (Top 10) with OBM三分钟论文竞赛(3MT)决赛 Top 10(OBM)
IGARSS 2025, BrisbaneIGARSS 2025,布里斯班
-
2025
IGARSS 2025 Travel GrantIGARSS 2025 Travel Grant 资助
IEEE GRSSIEEE GRSS
-
2021
Recommended for direct PhD admission (major rank 2/-)获推荐免试直博(专业排名第 2)
University of Electronic Science and Technology of China电子科技大学