Qihao Liu
Papers
1
Total Citations
15
H-Index
1
About
Qihao Liu is a researcher at the forefront of computer vision and robotics, with a focus on model-free, geometry-driven approaches for articulated object perception. His most influential work, "Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation" (2020, 15 citations), introduces an unsupervised vision system that estimates joint configurations of robot arms and articulated objects from RGB or RGB-D image sequences—without requiring any prior knowledge of the object model. By fusing classical geometric constraints with modern learning techniques, Liu’s method enables category-independent pose estimation, a breakthrough for robots interacting with unfamiliar, dynamic environments. This work has garnered attention for its elegant simplicity and practical applicability, earning citations from researchers in manipulation, scene understanding, and autonomous systems. Liu’s contributions stand out for bridging the gap between traditional geometry and data-driven vision, offering a robust foundation for future work in robotic perception and interactive AI.
Research Focus
Key Achievements
Top Papers
- 1