Morteza Rezanejad

McGill University, University of Toronto, McGill University Health Centre

Papers

Total Citations

H-Index

About

Morteza Rezanejad is a researcher whose work sits at the intersection of computational geometry, 3D shape analysis, and topological data analysis. His key research areas include environment mapping, shape representation, and 3D point cloud processing. Rezanejad’s major contributions include pioneering robust topological mapping techniques, such as the “flux skeleton” method for extracting road maps from unknown 2D environments, which offers a theoretically elegant and practical solution for autonomous navigation. He has also advanced 3D shape analysis through the development of “Medial Spectral Coordinates,” a novel framework that leverages medial structures for improved shape understanding. More recently, Rezanejad has pushed the boundaries of efficiency in 3D point cloud analysis with his work on “MLGCN,” an ultra-efficient graph convolutional neural network designed for tasks like model classification and segmentation. His most cited paper, “Robust environment mapping using flux skeletons” (2015), has garnered 12 citations, reflecting its foundational impact. With additional works in 3D shape analysis and point cloud processing, Rezanejad’s research demonstrates a consistent focus on creating robust, efficient, and theoretically grounded algorithms for spatial and geometric data, making significant strides in both robotics and computer vision.