Muhammad Asim
Papers
1
Total Citations
4
H-Index
1
About
Muhammad Asim’s research lies at the intersection of computer vision, robotics, and deep learning, with a particular focus on solving perception challenges for transparent and reflective objects. His most cited work, “DistillGrasp: Integrating Features Correlation With Knowledge Distillation for Depth Completion of Transparent Objects” (2024, 4 citations), addresses a critical bottleneck in robotic manipulation: the inability of standard RGB-D sensors to capture accurate depth from transparent surfaces due to reflection and refraction. Rather than simply designing more complex networks, Asim introduces a novel knowledge distillation framework that correlates visual features to reconstruct missing depth points with high fidelity. This approach not only improves grasp planning for robots handling transparent objects—such as glassware or acrylic—but also reduces model complexity, making deployment more practical. His work is notable for bridging the gap between theoretical feature correlation and real-world robotic applications. Asim’s contributions are already influencing the development of more robust perception systems in manufacturing, logistics, and service robotics, where transparent materials are common yet notoriously difficult to sense.
Research Focus
Key Achievements
Top Papers
- 1