John S. Papadakis

University of North Carolina at Charlotte

Papers

Total Citations

H-Index

About

John S. Papadakis is a researcher advancing the frontiers of 3D perception and robotic sensing. His primary contributions lie in the efficient processing of point cloud data and the calibration of RGBD sensors—critical areas for computer vision, graphics, and autonomous robotics. His most influential work, "Towards real-time segmentation of 3D point cloud data into local planar regions" (2017, 10 citations), introduces a novel algorithm that enables rapid, real-time decomposition of complex 3D scenes into planar surfaces. This capability is foundational for applications ranging from mapping and navigation to object recognition, directly addressing a bottleneck in real-time robotic perception. Papadakis further refined sensor utility in "Linear depth reconstruction for RGBD sensors" (2017, 2 citations), where he tackled the underexplored challenge of correcting depth measurement noise in consumer-grade cameras, providing a linear model that enhances the accuracy of mapping and localization systems. While his citation counts reflect a focused, early-career impact, his work on planar segmentation is particularly notable for its generic applicability, offering a practical solution for researchers integrating 3D data into AI and robotics pipelines. Papadakis’s research continues to shape how machines understand and interact with three-dimensional environments.