Lorenzo Manoni

About

Lorenzo Manoni is a researcher at the forefront of efficient deep learning for autonomous systems, specializing in real-time semantic segmentation and its integration with visual SLAM (Simultaneous Localization and Mapping). His most influential work, "A Low-Rank CNN Architecture for Real-Time Semantic Segmentation in Visual SLAM Applications" (2022), addresses a critical bottleneck in autonomous driving and robotics: performing computation-intensive semantic understanding on resource-constrained embedded devices. By introducing a novel low-rank convolutional neural network architecture, Manoni achieves significant reductions in model complexity and latency without sacrificing segmentation accuracy, enabling real-time scene parsing for smart vehicles and robots. This work has garnered 8 citations, reflecting its relevance to the growing demand for efficient, on-device AI. Manoni’s contributions bridge the gap between high-performance computer vision and practical deployment, tackling the dual challenges of low latency and computational efficiency that define modern autonomous navigation. His research is pivotal for advancing smart transportation and robotics, where every millisecond counts.

Research Focus

Key Achievements

Top Papers

1. 1
   A Low-Rank CNN Architecture for Real-Time Semantic Segmentation in Visual SLAM Applications

   8 citations · 2022

Key Collaborators

Contact & Links