Zhengrong Li

Papers

Total Citations

H-Index

About

Zhengrong Li is a leading researcher in computer vision and robotics, with a primary focus on monocular visual odometry (VO) and depth estimation. Li’s most influential work, “Improving Monocular Visual Odometry Using Learned Depth” (2022, 37 citations), tackles the long-standing challenge of building accurate and robust VO systems that operate reliably across diverse environments. By integrating learned monocular depth estimation into the VO pipeline, Li’s framework significantly enhances trajectory accuracy and robustness, addressing a critical bottleneck in autonomous navigation and augmented reality. This contribution bridges the gap between classical geometric methods and modern deep learning approaches, offering a practical solution for real-world deployment. Li’s research has been widely recognized for its impact on the field, with the 2022 paper serving as a key reference for subsequent work in self-supervised depth learning and visual localization. Beyond this, Li has contributed to advancing the understanding of how learned priors can compensate for the inherent scale ambiguity in monocular systems. For students and researchers, Li’s work exemplifies the power of combining data-driven techniques with traditional geometric reasoning to solve fundamental problems in visual perception.