Xinyu Gu

Chongqing University of Posts and Telecommunications

Papers

Total Citations

H-Index

About

Xinyu Gu is a leading researcher in autonomous navigation and computer vision, with a primary focus on visual odometry (VO) for self-driving vehicles, robotics, and augmented reality. Their most-cited work, "Visual Odometry with Deep Learning for Joint Semantic Segmentation" (2024), tackles a critical challenge in the field: the scale ambiguity and large pose estimation errors that plague existing learning-based VO methods. By integrating deep learning with semantic segmentation, Gu’s approach enables more robust motion estimation from visual sensors, directly improving the reliability of autonomous systems in real-world environments. With over 1 citation already, this paper is gaining traction as a foundational contribution to the next generation of VO systems. Gu’s research bridges the gap between perception and localization, offering practical solutions for safer, more accurate autonomous navigation. Their work is particularly notable for its interdisciplinary approach, combining deep learning, computer vision, and robotics to push the boundaries of what visual sensors can achieve. For students and researchers, Gu’s contributions highlight the importance of semantic understanding in motion estimation, making their work essential reading for anyone advancing autonomous vehicle technology or augmented reality systems.