HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Tue, 22 Apr 2025 12:33:27 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68078c97-27f8" expires: Mon, 29 Dec 2025 04:04:24 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 9FEB:2B0FD4:8416E2:946EC6:6951FB6F accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 03:54:24 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210046-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766980465.575247,VS0,VE212 vary: Accept-Encoding x-fastly-request-id: 5e39e654ae32e75313e34879ac78556e8aca4615 content-length: 2775

Siyan Dong (董思言)

I am a postdoctoral research fellow at HKU School of Computing and Data Science (HKUCDS) and HKU Musketeers Foundation Institute of Data Science (HKU IDS), working with Prof. Yanchao Yang and Prof. Yi Ma. My research interests span across the interdisciplinary fields of computer vision, graphics, and robotics. Specifically, I focus on 3D reconstruction and generation from images to support the development of 3D foundation models and embodied AI.

I received my PhD in computer science at Interdisciplinary Research Center (IRC), Shandong University, supervised by  Prof. Baoquan Chen. During my PhD,  I was a visiting researcher in the Computer Vision and Geometry Group (CVG), ETH Zurich, advised by Prof. Marc Pollefeys. I spent most of my research time in the Visual Computing and Learning Lab (VCL), Peking University, where I also remotely collaborated with Prof. Leonidas J. Guibas and Prof. Thomas Funkhouser. Before that, I was a research intern in the Advanced Innovation Center for Future Visual Entertainment (AICFVE), in Beijing Film Academy, in collaboration with Prof. Kai Xu.

Email: siyandong.3 [at] gmail.com
Google Scholar  /  Github

Selected Publications

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Yuzheng Liu*, Siyan Dong*†, Shuzhe Wang, Yingda Yin, Yanchao Yang†, Qingnan Fan, Baoquan Chen†

CVPR 2025 (Highlight), top 13.5% of accepted papers

Paper  /  Code

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Siyan Dong*, Shuzhe Wang*, Shaohui Liu, Lulu Cai, Qingnan Fan, Juho Kannala, Yanchao Yang

CVPR 2025

Paper  /  Code

InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction

Xulong Wang*, Siyan Dong*, Youyi Zheng, Yanchao Yang

ECCV 2024

Paper  /  Code

SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization

Yiyang Chen*, Siyan Dong*, Xulong Wang, Lulu Cai, Youyi Zheng, Yanchao Yang

ECCV 2024

Paper  /  Code

Lazy Visual Localization via Motion Averaging

Siyan Dong*, Shaohui Liu*, Hengkai Guo, Baoquan Chen, Marc Pollefeys

Technical Report

Visual Localization via Few-Shot Scene Region Classification

Siyan Dong*, Shuzhe Wang*, Yixin Zhuang, Juho Kannala, Marc Pollefeys, Baoquan Chen

3DV 2022

Paper  /  Code  /  Video

Towards Accurate Active Camera Localization

Qihang Fang*, Yingda Yin*, Qingnan Fan, Fei Xia, Siyan Dong, Sheng Wang, Jue Wang, Leonidas Guibas, Baoquan Chen

ECCV 2022

Paper  /  Code  /  Video

Multi-Robot Active Mapping via Neural Bipartite Graph Matching

Kai Ye*, Siyan Dong*, Qingnan Fan, He Wang, Li Yi, Fei Xia, Jue Wang, Baoquan Chen

CVPR 2022

Paper  /  Code  /  Video

Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

Siyan Dong*, Qingnan Fan*, He Wang, Ji Shi, Li Yi, Thomas Funkhouser, Baoquan Chen, Leonidas Guibas

CVPR 2021 (Oral)

Paper  /  Code  /  Video  /  Poster

Multi-Robot Collaborative Dense Scene Reconstruction

Siyan Dong, Kai Xu, Qiang Zhou, Andrea Tagliasacchi, Shiqing Xin, Matthias Nießner, Baoquan Chen

ACM Transactions on Graphics & SIGGRAPH 2019

Paper  /  Code

Professional Service

Conference Reviewer: CVPR, ECCV, ICCV, SIGGRAPH, SIGGRAPH Asia

Journal Reviewer: T-RO, RA-L, TMM