Fahim Mannan

Papers

Total Citations

H-Index

About

Fahim Mannan is a researcher whose work lies at the intersection of computer vision, robotics, and autonomous systems, with a particular focus on real-world perception challenges. His key contributions address the critical problem of stereo vision calibration in dynamic environments, where traditional methods often fail. In his notable work, "Flow-Guided Online Stereo Rectification for Wide Baseline Stereo" (2024), Mannan tackles the underappreciated issue of maintaining accurate stereo rectification in autonomous vehicles and robots operating in-the-wild. These systems are constantly subjected to environmental stressors like vibration and structural strain, which degrade calibration over time. By introducing a flow-guided approach, Mannan provides a solution for continuous, online recalibration—a significant advancement for real-world deployment. While his most-cited paper has garnered 3 citations, its impact is poised to grow as the field increasingly recognizes the practical necessity of robust, self-correcting vision systems. Mannan’s work bridges a crucial gap between laboratory-perfect algorithms and the messy, unpredictable conditions of real-world operation, making him a key contributor to the next generation of resilient autonomous perception.