Seongmin Kang
Papers
1
Total Citations
25
H-Index
1
About
Seongmin Kang is a leading researcher in robotic manipulation and computer vision, with a particular focus on solving the challenges of perceiving and grasping transparent objects. His most-cited work, "GhostPose: Multi-view Pose Estimation of Transparent Objects for Robot Hand Grasping" (2021, 25 citations), directly tackles a critical bottleneck in industrial and service robotics: the inability of standard depth sensors to accurately capture transparent surfaces. Kang’s major contribution lies in developing a multi-view pose estimation framework that overcomes these limitations, enabling robots to reliably infer the 3D position and orientation of glass, plastic, and other see-through items. This work has significant implications for automation in logistics, manufacturing, and domestic assistance, where transparent objects are ubiquitous. By bridging the gap between sensor constraints and real-world grasping demands, Kang’s research has garnered attention from both academia and industry, establishing him as a key innovator in vision-based robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1