Liusheng Sun
Papers
1
Total Citations
5
H-Index
1
About
Liusheng Sun is a rising researcher in autonomous driving perception, with a focus on efficient multi-modal depth estimation. His work centers on fusing radar and camera data to produce dense, metric depth maps—a critical capability for real-time navigation in autonomous vehicles and robotics. Sun’s major contribution, demonstrated in his highly cited paper “TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion” (2025, 5 citations), addresses the challenge of radar signal sparsity by proposing a one-stage fusion framework that avoids the computational overhead of two-stage methods. This innovation enables faster, more accurate depth prediction without sacrificing performance, directly tackling the trade-off between model efficiency and accuracy. Sun’s research is notable for its practical impact, targeting real-world deployment constraints like low latency and limited hardware resources. His work has quickly garnered attention, with citations reflecting its relevance to the growing field of sensor fusion for autonomous systems. By advancing radar-camera depth estimation, Sun is helping pave the way for safer, more reliable self-driving technology.
Research Focus
Key Achievements
Top Papers
- 1