Lorenzo Papa
Papers
4
Total Citations
30
H-Index
3
About
Lorenzo Papa is a researcher at the forefront of efficient computer vision, specializing in monocular depth estimation (MDE) for resource-constrained environments. His work tackles the critical challenge of enabling real-time 3D scene understanding on low-power IoT and embedded devices, a key enabler for autonomous systems and robotics. Papa’s major contributions include the development of **SPEED** (Separable Pyramidal Pooling Encoder-Decoder), a lightweight architecture achieving real-time depth prediction with minimal computational overhead, which has garnered 16 citations. He has systematically benchmarked MDE models across both terrestrial and underwater scenarios, demonstrating that accurate depth perception is feasible even on energy-limited hardware. His recent investigations into optimizing Vision Transformer architectures with efficient attention modules (2024) further push the boundaries of accuracy-efficiency trade-offs. With a growing body of work accumulating over 30 citations, Papa’s research is instrumental in democratizing advanced perception for edge devices, bridging the gap between deep learning performance and real-world deployment constraints.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4