Skip to content
photo-siyan-dong-2
Dr DONG Siyan
Post-doctoral Fellow
HKU Musketeers Foundation Institute of Data Science
About me

Dr Siyan Dong is a Post-doctoral Research Fellow at the HKU Musketeers Foundation Institute of Data Science, working with Prof Yanchao Yang, Prof Difan Zou, and Prof Yi Ma. Siyan received his PhD in computer science from Shandong University, supervised by Prof Baoquan Chen. During his PhD, he was a visiting researcher at the Computer Vision and Geometry Group, ETH Zurich, advised by Prof Marc Pollefeys. He spent most of his research time at the Visual Computing and Learning Lab at Peking University, where he also remotely collaborated with Prof Leonidas J. Guibas at Stanford University. Before that, he was a research intern at the Advanced Innovation Center for Future Visual Entertainment in Beijing Film Academy. His research interests span across the interdisciplinary fields of computer vision and robotics. Specifically, he focuses on 3D reconstruction and generation from images to support embodied AI and the development of 3D foundation models.

Current Research Project

Siyan is exploring foundational models on 3D geometry to aid embodied agents. His work includes passive and active pose estimation, 3D object and scene reconstruction, generation, and dynamics prediction from images or videos. He is also open to any challenging research topics in artificial intelligence and data science.

Selected Publications
  • Siyan Dong, Shuzhe Wang, Yixin Zhuang, Juho Kannala, Marc Pollefeys, Baoquan Chen. “Visual Localization via Few-Shot Scene Region Classification.” International Conference on 3D Vision (3DV) 2022.
  • Siyan Dong, Qingnan Fan, He Wang, Li Yi, Fei Xia, Jue Wang, Baoquan Chen. “Multi-Robot Active Mapping via Neural Bipartite Graph Matching.” Conference on Computer Vision and Pattern Recognition (CVPR) 2022.
  • Siyan Dong, Qingnan Fan, He Wang, Ji Shi, Li Yi, Thomas Funkhouser, Baoquan Chen, Leonidas J Guibas. “Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments.” Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
  • Siyan Dong, Kai Xu, Qiang Zhou, Andrea Tagliasacchi, Shiqing Xin, Matthias Nießner, Baoquan Chen. “Multi-Robot Collaborative Dense Scene Reconstruction.” Transactions on Graphics (TOG) 2019.

Research Interests

Computer Vision, Graphics, Robotics, Machine Learning