Marco Manfredi

Papers

Total Citations

H-Index

About

Marco Manfredi is a leading researcher in visual localization and cross-view geolocation, with a focus on enabling autonomous vehicles and robots to determine their position with high precision. His work bridges the gap between ground-level imagery and overhead satellite or aerial views—a challenging problem due to dramatic differences in perspective, scale, and appearance. Manfredi’s most influential paper, “Visual Cross-View Metric Localization with Dense Uncertainty Estimates” (2022, 34 citations), introduces a method that not only matches ground and aerial images but also provides dense uncertainty estimates, greatly improving reliability for real-world navigation. His earlier work, “Cross-View Matching for Vehicle Localization by Learning Geographically Local Representations” (2021, 21 citations), pioneered the use of geographically local features to make cross-view matching robust across diverse environments. By learning shared representations that capture location-specific visual cues, Manfredi has advanced self-localization techniques that do not rely on GPS. His contributions are vital for autonomous driving, drone navigation, and robotics, where accurate, uncertainty-aware positioning is critical. With a growing citation record and innovative approaches to a fundamental problem, Manfredi is shaping the future of visual-based localization.