Hongxuan Guo

Papers

Total Citations

H-Index

About

Hongxuan Guo is a researcher advancing the frontiers of computer vision and robotic perception, with a primary focus on 6D pose estimation and adaptive feature fusion. His most cited work, "A novel adaptive weighted fusion network based on pixel level feature importance for two-stage 6D pose estimation" (2025), introduces a groundbreaking approach that dynamically weights pixel-level features to improve accuracy in object pose estimation. This method addresses a critical challenge in robotics and augmented reality: precisely determining an object's position and orientation in three-dimensional space from two-dimensional images. By developing a two-stage framework that leverages adaptive fusion, Guo enables more robust performance under occlusion and varying lighting conditions. His contributions are particularly impactful for autonomous systems, where reliable pose estimation is essential for manipulation and navigation. With his work already garnering early citations, Guo is establishing himself as an emerging voice in the field. His research not only pushes the boundaries of deep learning architectures but also provides practical solutions for real-world applications, making him a promising figure for students and researchers interested in the intersection of machine learning and spatial understanding.