Max Robotics — Global Service Robot Directory + US Certification

About

Yaqing Ding is a rising researcher in computer vision and robotics, whose work focuses on the critical challenges of sensor calibration, motion estimation, and 3D scene understanding. His research spans from geometric computer vision—particularly camera motion estimation and multi-camera systems—to point cloud registration and sensor fusion for autonomous systems. Ding’s most cited work, “A two-step approach to Lidar-Camera calibration” (2021, 6 citations), introduces a coarse-to-fine method for external calibration, a fundamental requirement for autonomous vehicles and robots that rely on both Lidar and camera data for ego-motion estimation and scene understanding. He further advanced multi-camera systems with “Globally Optimal Relative Pose Estimation for Multi-Camera Systems with Known Gravity Direction” (2022, 5 citations), leveraging IMU-derived gravity to achieve globally optimal pose estimation. More recently, his paper “SGNet: Salient Geometric Network for Point Cloud Registration” (2024, 2 citations) addresses the persistent challenge of identifying geometrically and semantically consistent points across scans. Ding’s contributions also include a general elimination strategy for camera motion estimation, demonstrating his systematic approach to solving fundamental geometric problems. His work is increasingly cited in the autonomous driving and robotics communities, establishing him as a promising voice in sensor fusion and geometric vision.