Baoqi Huang

Papers

Total Citations

H-Index

About

Baoqi Huang is a researcher advancing the frontiers of visual odometry (VO) and simultaneous localization and mapping (SLAM), with a focus on enabling robust robot navigation in challenging real-world conditions. His key contributions center on improving the accuracy and reliability of VO systems in environments plagued by dynamic textures, poor lighting, and rapid motion. Huang’s most notable work, "MAS-DSO: Advancing Direct Sparse Odometry With Multi-Attention Saliency" (2024), introduces a novel multi-attention saliency mechanism that significantly enhances feature selection and tracking performance, directly addressing the limitations of traditional methods. This paper has already garnered 5 citations, signaling its growing impact in the field. By integrating attention-based deep learning into direct sparse odometry, Huang’s research offers a practical pathway for deploying SLAM in autonomous vehicles, drones, and mobile robots. His work represents a meaningful step toward more resilient perception systems, earning recognition among peers for its technical depth and applicability. For students and researchers exploring VO, Huang’s contributions provide a compelling example of how attention mechanisms can overcome longstanding environmental challenges.