Xiaopeng Li
Papers
1
Total Citations
22
H-Index
1
About
Xiaopeng Li is a researcher specializing in 3D computer vision, with a particular focus on point cloud processing and autonomous perception systems. His work sits at the intersection of deep learning and spatial understanding, addressing critical challenges in how machines interpret three-dimensional environments. Li's most recognized contribution is PSANet (Pyramid Splitting and Aggregation Network), a one-stage 3D object detection framework designed for LiDAR point cloud data. Published in 2020 and accumulating 22 citations, this work tackles a fundamental limitation in autonomous driving perception: the insufficient utilization of bird's-eye view feature representations in existing detectors. By introducing pyramid-based feature splitting and aggregation strategies, PSANet improves detection accuracy while maintaining the computational efficiency demanded by real-time applications in autonomous vehicles, intelligent robotics, and augmented reality systems. Li's research speaks directly to some of the most pressing engineering challenges of our time — enabling machines to reliably perceive and navigate physical spaces. His contributions to one-stage detection architectures demonstrate a commitment to balancing performance with practicality, a balance essential for deploying AI systems in safety-critical real-world environments. His work provides a valuable foundation for students and researchers exploring perception pipelines in autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1