Papers

2

Total Citations

17

H-Index

2

About

Hameed Abdul-Rashid is a researcher advancing the frontiers of 3D scene understanding and robotic manipulation through perception. His work centers on two key areas: inferring kinematic structures from visual data and bridging the gap between 2D images and 3D scenes. In his most cited paper, "Learning to Infer Kinematic Hierarchies for Novel Object Instances" (2022, 9 citations), Abdul-Rashid tackles the challenging problem of enabling robots to perceive the complete kinematic hierarchy—parts, motions, and couplings—of never-before-seen articulated objects, a critical step for autonomous manipulation. This work moves beyond prior methods that relied on known object models, offering a more generalizable approach. His earlier contribution, "2D Image-Based 3D Scene Retrieval" (2018, 8 citations), pioneered a new research direction by allowing users to search for relevant 3D scenes using a simple 2D image, creating an intuitive framework for learning and utilizing 3D data. Together, these contributions demonstrate his impact in making 3D perception more accessible and actionable, with applications in robotics, computer vision, and interactive systems. Abdul-Rashid’s research is shaping how machines understand and interact with the physical world.

Research Focus

Key Achievements

2
H-Index
2
Papers
17
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
Learning to Infer Kinematic Hierarchies for Novel Object Instances
9 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 29
🏛 Institutions: University of Illinois Urbana-Champaign, University of Southern Mississippi

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago