Tam Sobeih
Papers
1
Total Citations
2
H-Index
1
About
Tam Sobeih is a rising researcher at the intersection of computer vision and neuromorphic engineering, with a primary focus on energy-efficient depth estimation using event cameras. Their most notable contribution is the development of a novel spike transformer network that achieves state-of-the-art depth estimation from asynchronous event data, while dramatically reducing computational cost. By pioneering cross-modality knowledge distillation, Sobeih’s work bridges the gap between traditional frame-based vision and emerging event-based sensors, enabling practical deployment in power-constrained systems like autonomous drones and robotics. This flagship paper, published in 2025, has already garnered 2 citations, signaling growing influence in the field. Sobeih’s research directly addresses the critical challenge of balancing high dynamic range and low latency with energy efficiency—a key bottleneck for real-time autonomous navigation and augmented reality applications. Their innovative approach to leveraging spike-based neural networks for depth perception marks a significant step toward biologically inspired, sustainable AI systems. As the field of neuromorphic vision accelerates, Sobeih’s work positions them as a promising voice in the quest for efficient, event-driven perception.
Research Focus
Key Achievements
Top Papers
- 1