Papers
3
Total Citations
25
H-Index
3
About
Shijian Lu is a researcher whose work spans computer vision, autonomous systems, and human-computer interaction, with a particular focus on 3D perception for real-world applications. His most impactful contributions lie in the domain of 3D object detection and tracking using LiDAR point clouds — technologies fundamental to autonomous driving and robotics. In his 2023 paper "TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection," Lu and his collaborators advanced the field by incorporating temporal information from point cloud sequences, moving beyond the limitations of single-frame analysis to achieve more robust scene understanding. Building on this trajectory, his 2024 work on continuous motion modeling for 3D single object tracking further refined how AI systems interpret dynamic environments by leveraging longer temporal contexts rather than relying solely on frame-pair comparisons. His earlier research, including a 2003 study on web-based telerobotics at the National University of Singapore, demonstrates a longstanding interest in making advanced technology remotely accessible. With publications accumulating citations across multiple cutting-edge domains, Lu represents a researcher whose contributions are steadily shaping the future of intelligent perception systems in autonomous and robotic platforms.
Research Focus
Key Achievements
Top Papers
- 1TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection15 citations · 2023
- 2Modeling Continuous Motion for 3D Point Cloud Object Tracking6 citations · 2024
- 3Web-based Robot for Remote Experiments4 citations · 2003
Key Collaborators
Related papers
- LiDAR-based 3D object detection and tracking for autonomous driving
- Modeling Continuous Motion for 3D Point Cloud Object Tracking
- Modeling Continuous Motion for 3D Point Cloud Object Tracking
- TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection
- Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking
Researchers in this area
Labs working in this area
If you're exploring the applied side
Commercial systems in adjacent areas you may find useful as a starting point. This is not a claim that the research here is used in them — academia and industry often move on separate tracks.
Suggested by topic similarity — not advertising or endorsement.