Bingxi Liu

Southern University of Science and Technology

Papers

Total Citations

H-Index

About

Bingxi Liu is a researcher whose work lies at the intersection of computer vision, robotics, and augmented reality, with a particular focus on visual place recognition (VPR). His most-cited paper, "Deep Homography Estimation for Visual Place Recognition" (2024, 17 citations), addresses a fundamental challenge in enabling machines to reliably identify and localize themselves within environments. Liu’s major contribution lies in advancing hierarchical VPR methods, which balance accuracy and computational efficiency by first employing global features for coarse localization before refining matches. This approach is critical for real-world applications like robot navigation and AR systems, where speed and precision are equally vital. By integrating deep homography estimation into the VPR pipeline, Liu has enhanced the robustness of place recognition under challenging conditions such as viewpoint changes. His work is gaining traction among researchers seeking scalable solutions for autonomous systems. With a growing citation footprint, Liu is establishing himself as a promising voice in the field, pushing the boundaries of how machines perceive and navigate the physical world.