About Me
Hi, I’m Guanghao Li, currently based in Shanghai, China.
I am interested in Robotics, specifically 3D reconstruction using differentiable rendering and Visual-Inertial SLAM (VI-SLAM). Looking ahead, I hope to expand my work into motion control and active exploration.
Outside the lab, I enjoy exploring the outdoors. I love taking road trips through uninhabited areas and climbing snow mountains, with a personal goal of traveling the world. I am also passionate about applying my research to these hobbies. By using low-cost vision and IMU sensors, I aim to achieve reliable trajectory recording, offline map matching, and even navigation in extreme outdoor environments.
Currently, I am preparing to climb Qizi Peak, the South/North slopes of Yuzhu Peak, and Mt. Jinyin.
I expect to graduate around 2027/2028 and am actively looking for Postdoc, Researcher, or Engineer positions. Maybe Alpine Guide / Expedition Leader is also suitable for me. Feel free to reach out.
Publications
PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM
Guanghao Li, Yu Cao, Qi Chen, Xin Gao, Yifan Yang, Jian Pu
PAPL-SLAM is a point-line SLAM system that efficiently integrates line structural information and optimization by anchoring lines to a principal axis, reducing the number of parameters, and utilizing probabilistic data association, enabling robust, rapid, and accurate mapping and tracking in both indoor and outdoor environments.
Multi-LIO: A Lightweight Multiple LiDAR-Inertial Odometry System
Qi Chen*, Guanghao Li*, Xiangyang Xue, Jian Pu
Multi-LIO is a real-time, computationally efficient multiple LiDAR-inertial odometry system that enhances accuracy and scalability, using parallel state updates, voxelized maps, and point-wise uncertainty estimation to improve scan-to-map registration in large-scale, complex environments.
Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Jian Pu, Mulin Yu, Jiangmiao Pang
ARTDECO unifies 3D foundation priors with structured scene representations, enabling robust and generalizable 3D reconstruction of diverse real-world scenes using only monocular video.
Constrained Gaussian Splatting via Implicit TSDF Hash Grid for Dense RGB-D SLAM
Guanghao Li, Qi Chen, Sijia Hu, Yuxiang Yan, Jian Pu
FusionMap is an advanced SLAM system that combines explicit 3DGS and implicit NeRF representations to improve surface reconstruction accuracy. By addressing the limitations of traditional 3DGS, FusionMap achieves up to 30 times faster processing and a 38% accuracy boost over conventional methods. This innovation sets new standards for real-time 3D mapping and localization, enabling next-generation applications in virtual environments, autonomous navigation, and dynamic scene reconstruction.
Guanghao Li, Qi Chen, Yuxiang Yan, Jian Pu
EC-SLAM is a real-time dense RGB-D SLAM system that leverages Neural Radiance Fields (NeRF) for enhanced pose optimization, using sparse parametric encodings, TSDF, and a globally constrained Bundle Adjustment strategy to improve tracking accuracy and reconstruction performance in real-time.
