Papers
1
Total Citations
37
H-Index
1
About
Han Xue is a rising researcher in computer vision and robotics, whose work pushes the boundaries of how machines perceive and interact with the physical world. Her primary research focuses on category-level articulation pose estimation, a critical challenge for enabling robots to manipulate everyday objects like cabinets, doors, and tools. In her highly cited 2022 paper, "Toward Real-World Category-Level Articulation Pose Estimation," Xue tackles the limitations of prior methods that assume fixed kinematic structures for each object category. Instead, she pioneers approaches that estimate part-level 6D poses across diverse, real-world instances—a breakthrough for practical robotics. Garnering 37 citations, this work has already influenced subsequent studies in embodied AI and scene understanding. Xue’s contributions are notable for bridging the gap between controlled lab settings and the messy, variable environments of human life, where articulated objects are ubiquitous. Her research not only advances fundamental computer vision but also holds promise for applications in assistive robotics, autonomous navigation, and augmented reality. As a young scholar, Han Xue is establishing herself as a key voice in making machines truly capable of understanding and acting within our dynamic, articulated world.
Research Focus
Key Achievements
Top Papers
- 1Toward Real-World Category-Level Articulation Pose Estimation37 citations · 2022