Shaoshuai Shi
Papers
1
Total Citations
79
H-Index
1
About
Shaoshuai Shi is a leading researcher in 3D computer vision, with a focus on point cloud perception and temporal object detection for autonomous driving. His work addresses the critical challenge of understanding dynamic 3D environments from LiDAR data, where objects must be detected and tracked across time. Shi’s most notable contribution is the development of MPPNet (Multi-frame Feature Intertwining with Proxy Points), a novel framework for 3D temporal object detection that efficiently aggregates information across multiple LiDAR frames. By introducing “proxy points” to represent object candidates, MPPNet enables robust feature intertwining without the computational burden of dense point cloud processing, achieving state-of-the-art performance on benchmarks like Waymo Open Dataset. This work has garnered 79 citations since its 2022 publication, reflecting its immediate impact on the field. Shi’s research bridges the gap between single-frame detection and long-term temporal reasoning, offering practical solutions for real-time autonomous systems. His contributions are widely recognized as foundational for advancing reliable 3D perception in complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1