Rokia Abdein

Papers

Total Citations

H-Index

About

Rokia Abdein is a rising researcher at the forefront of 3D computer vision and geometric deep learning. Her work focuses on advancing scene flow estimation—a critical task for understanding dynamic environments from point cloud data—by integrating novel neural architectures. In her most-cited paper, "Deep scene flow learning from point cloud with Transformer" (2025), she pioneers the use of Transformer-based models to capture long-range dependencies in unstructured 3D data, achieving superior accuracy in motion prediction. This contribution addresses a key limitation of prior convolutional approaches, enabling more robust perception for autonomous systems and robotics. Though early in her career, her work has already garnered 4 citations, signaling growing recognition in the field. Abdein’s research bridges the gap between efficient point cloud processing and high-level scene understanding, with potential applications in self-driving vehicles, augmented reality, and dynamic mapping. Her innovative use of attention mechanisms marks her as a promising voice in the next generation of 3D vision researchers, poised to shape how machines interpret and interact with moving environments.