John McCormac

Dyson (United Kingdom), Imperial College London

Papers

Total Citations

701

H-Index

About

John McCormac is a researcher specializing in computer vision, robotics, and semantic 3D mapping, with a particular focus on enabling machines to understand and interact with their environments at a deeper level. He is best known for his pioneering work on **SemanticFusion**, a system that integrates convolutional neural networks with dense 3D mapping to produce rich, semantically annotated reconstructions of real-world environments. Published in 2017, this work addressed a critical challenge in robotics: moving beyond purely geometric maps to ones that incorporate object-level understanding, dramatically improving robot intelligence and human-robot interaction. The paper has garnered over 657 citations, establishing it as a landmark contribution in the field. An earlier workshop version of the work, presented in 2016, further demonstrates McCormac's sustained commitment to advancing this research direction. His contributions have had significant influence on downstream tasks such as autonomous navigation, scene understanding, and augmented reality. By bridging deep learning and simultaneous localization and mapping (SLAM), McCormac has helped shape a new generation of spatially and semantically aware robotic systems, making his work essential reading for anyone working at the intersection of computer vision and mobile robotics.