Papers
1
Total Citations
9
H-Index
1
About
Ali Thabet is a leading researcher in 3D deep learning, with a focus on efficient neural architecture design for point cloud processing. His work addresses the critical challenge of balancing accuracy with computational constraints in real-world 3D applications. Thabet is best known for his contributions to automated architecture search for point cloud networks, exemplified by his highly cited paper "LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks" (2022, 9 citations). This work pioneered a framework that automatically discovers optimal network architectures while respecting latency budgets, bridging the gap between high-performance 3D models and practical deployment on resource-limited devices. Beyond NAS, Thabet has made significant advances in point cloud classification, segmentation, and detection, helping to establish automated design as a viable alternative to handcrafted architectures. His research has been instrumental in making 3D deep learning more accessible and efficient, with his methods influencing subsequent work in the field. Thabet continues to push the boundaries of automated 3D perception, enabling smarter, faster, and more practical solutions for autonomous systems, robotics, and augmented reality.
Research Focus
Key Achievements
Top Papers
- 1