Hunter Schofield

Papers

Total Citations

H-Index

About

Hunter Schofield is an emerging researcher specializing in computer vision, robotics perception, and sensor fusion, with a particular focus on fiducial marker systems and image processing for real-world robotic applications. His work addresses critical challenges in enabling robots to reliably perceive and interact with their environments under imperfect conditions. Schofield's most notable contributions include the development of Ghost-DeblurGAN, a lightweight generative adversarial network designed for real-time motion deblurring, which directly tackles the problem of feature detection failure caused by motion blur in dynamic robotic settings. This work has garnered 16 citations since its 2022 publication, reflecting its practical relevance to the robotics community. Complementing this, his Intensity Image-based LiDAR Fiducial Marker (IILFM) system — cited 15 times — addresses a significant gap in LiDAR-based robotics by enabling fiducial marker detection from unstructured point clouds with intensity data, requiring no restrictive environmental assumptions. Together, these contributions demonstrate Schofield's commitment to developing robust, deployable perception solutions that bridge the gap between controlled laboratory settings and the unpredictable demands of real-world robotics. His research is establishing a meaningful foundation in multi-modal sensing and practical computer vision for autonomous systems.