Qianliang Wu

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Qianliang Wu is a rising researcher in computer vision and robotics, whose work focuses on geometric perception and multi-sensor fusion for autonomous systems. His most influential contribution addresses the challenging problem of globally optimal relative pose estimation for multi-camera systems, leveraging known gravity direction from IMU data—a practical innovation for self-driving cars, robots, and smartphones. This 2022 paper has already garnered 5 citations, reflecting its relevance to real-world applications where accurate, efficient pose estimation is critical. More recently, Wu introduced SGNet (Salient Geometric Network) for point cloud registration, a 2024 work that tackles the persistent challenge of identifying semantically and geometrically consistent keypoints across scans. With 2 citations in its first year, this research promises to advance 3D scene understanding and mapping. Wu’s work bridges theoretical rigor with practical deployment, addressing fundamental bottlenecks in autonomous navigation and perception. His contributions are particularly notable for their focus on globally optimal solutions and geometric saliency, setting a foundation for more robust, real-time systems. As the fields of autonomous driving and robotics continue to demand higher precision, Wu’s research is poised to have lasting impact.