Hannah Schieber
Papers
2
Total Citations
29
H-Index
2
About
Hannah Schieber is a leading researcher in 3D computer vision, with a primary focus on category-level 6D object pose estimation—a critical challenge for enabling robots and augmented reality systems to interact with everyday objects. Her major contribution is the creation of **HouseCat6D**, a large-scale, multi-modal dataset featuring household objects in realistic scenarios. This dataset directly addresses a key bottleneck in the field: the lack of high-quality, diverse annotations for category-level pose estimation. Unlike previous datasets that suffered from limited pose variety and poor annotation quality, HouseCat6D provides a robust benchmark that has already garnered over 29 citations in just two years, signaling its rapid adoption by the research community. By bridging the gap between instance-level and category-level approaches, Schieber’s work is paving the way for more practical, generalizable computer vision systems. Her research is particularly notable for its emphasis on real-world applicability, moving beyond controlled lab settings to tackle the messy, varied conditions of household environments—a crucial step for deploying AI in homes and industries.
Research Focus
Key Achievements
Top Papers
- 1
- 2