Papers
6
Total Citations
218
H-Index
5
About
Maxime Ferrera is a researcher specializing in visual simultaneous localization and mapping (SLAM), visual odometry, and autonomous navigation, with a particular focus on challenging and unconventional environments. His work bridges the gap between computer vision, robotics, and real-world deployment, addressing scenarios where traditional localization methods fall short. Ferrera's most celebrated contribution is OV²SLAM (2021), a fully online and versatile visual SLAM system designed for real-time applications across augmented reality, robotics, and autonomous driving — a work that has garnered over 100 citations, reflecting its broad utility and technical rigor. Equally impactful is his pioneering research into underwater visual odometry, where he tackled the formidable challenge of monocular localization in turbid and dynamic underwater conditions, earning 75 citations and demonstrating that camera-based navigation could rival expensive acoustic and navigational sensor systems. Beyond these flagship works, Ferrera has contributed to stereo disparity refinement through hybrid data-model fusion approaches and developed the Eiffel Tower deep-sea dataset, advancing long-term visual localization benchmarking in underwater settings. His doctoral work further unified monocular visual-inertial-pressure sensing for underwater 3D mapping. Across his portfolio, Ferrera consistently pushes visual navigation into demanding, underexplored domains.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6