Yujie Fang

National University of Defense Technology

Papers

Total Citations

H-Index

About

Yujie Fang is a researcher specializing in indoor localization, computer vision, and deep learning, with a particular focus on enhancing positioning accuracy in complex environments. Their most notable contribution is the development of a visual and variational autoencoder (VAE)-based hierarchical indoor localization method, which addresses the critical challenge of precise pose estimation without relying on expensive sensor arrays. By integrating visual data with a pre-built 3D model, Fang’s approach improves robustness in applications ranging from robotics and augmented reality to navigation services. This work, published in 2021, has garnered early recognition with 3 citations, signaling growing interest in their innovative fusion of generative models with traditional localization techniques. Fang’s research pushes the boundaries of how machines perceive and navigate indoor spaces, offering scalable solutions that reduce dependency on external infrastructure. Their work is particularly relevant for students and researchers exploring deep learning-driven spatial intelligence, as it demonstrates a practical pathway to achieving high-precision localization in GPS-denied settings.