Rabab Abdelfattah

Papers

Total Citations

H-Index

About

Rabab Abdelfattah is a researcher whose work sits at the intersection of computer vision, deep learning, and autonomous systems. Her research focuses on monocular depth estimation — the challenging problem of inferring three-dimensional spatial information from a single two-dimensional image, a capability fundamental to autonomous driving, robotics, and resource-constrained perception systems. In her notably cited work, "Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image" (2022), Abdelfattah advances the field by leveraging attention mechanisms within an encoder-decoder architecture to achieve accurate and efficient depth prediction without relying on expensive sensor hardware such as LIDAR or RADAR. This contribution is particularly significant as it addresses a core bottleneck in making intelligent systems more accessible and deployable in real-world dynamic environments. With 10 citations, her work has begun attracting the attention of the computer vision community, signaling growing recognition of her contributions. For students and researchers working in scene understanding, 3D reconstruction, or autonomous navigation, Abdelfattah's research represents a meaningful step toward practical, sensor-free depth perception solutions that balance accuracy with computational efficiency.