Yeong-Hun Park

Papers

Total Citations

H-Index

About

Yeong-Hun Park is a researcher advancing the frontiers of computer vision and robotics, with a particular focus on efficient monocular depth estimation. His work addresses a critical bottleneck in mobile robotics: achieving accurate depth perception from a single RGB camera while maintaining computational efficiency for real-time, low-power deployment. Park’s most cited paper, “Lightweight Monocular Depth Estimation via Token-Sharing Transformer” (2023, 6 citations), introduces a novel architecture that leverages a token-sharing mechanism within a transformer framework. This innovation significantly reduces model complexity without sacrificing depth accuracy, making it highly suitable for resource-constrained platforms like drones and autonomous ground vehicles. By enabling robust depth sensing with minimal hardware, Park’s contributions directly impact the practicality and scalability of autonomous navigation systems. His research bridges the gap between state-of-the-art deep learning and real-world deployment, offering a compelling solution for the growing demand for compact, cost-effective perception in robotics. Park’s work stands as a notable step toward making advanced depth estimation accessible for a wide range of mobile applications.