Weikai Tan

Papers

Total Citations

H-Index

About

Weikai Tan is a researcher advancing the frontiers of 3D perception and autonomous navigation. His work centers on geometric deep learning for point cloud analysis and robust Simultaneous Localization and Mapping (SLAM) in challenging indoor environments. Tan’s most cited contribution, “GRNet: Geometric Relation Network for 3D Object Detection from Point Clouds” (2020, 26 citations), introduces a novel architecture that explicitly models spatial relationships between points, significantly improving detection accuracy in cluttered 3D scenes—a foundational step for applications in robotics and autonomous driving. More recently, his paper “SLAM-TSM: Enhanced Indoor LiDAR SLAM With Total Station Measurements for Accurate Trajectory Estimation” (2024) tackles the persistent problem of drift in feature-poor or repetitive indoor spaces by fusing LiDAR data with total station measurements, achieving centimeter-level trajectory accuracy where conventional methods fail. This work directly addresses critical gaps in indoor navigation for intelligent robotics and computer vision. With a growing citation footprint and a focus on bridging geometric reasoning with real-world sensor fusion, Tan’s research is shaping more reliable perception and localization systems for next-generation autonomous platforms.