Pearl Pu

University of Pennsylvania, École Normale Supérieure - PSL

Papers

Total Citations

H-Index

About

Pearl Pu is a pioneering researcher whose work bridges computer vision and intelligent spatial planning. Her most influential contribution, "A New Development in Camera Calibration: Calibrating a Pair of Mobile Cameras" (1987, 33 citations), introduced a novel method for calibrating mobile cameras as a function of their position and orientation. This breakthrough enabled active visual sensing for three-dimensional scene analysis, laying foundational groundwork for modern robotics and augmented reality systems. Pu's research demonstrates a rare ability to solve practical engineering challenges—her calibration technique allowed cameras to adapt dynamically to movement, a critical capability for autonomous navigation and 3D reconstruction. Beyond vision, Pu explored cognitive approaches to robotics through her work on means-ends analysis for spatial planning (1992, 2002). She proposed that robots could overcome limitations of traditional pathfinding by reasoning about moving obstacles, much like humans do. While these papers have modest citation counts, they represent an early, prescient attempt to infuse spatial reasoning with psychological principles. Pu's career exemplifies how technical precision in calibration methods can unlock broader advances in intelligent systems, inspiring subsequent work in both computer vision and robotic planning.