MBZUAI graduate wins IEEE MetaCom Best Ph.D. Forum Paper Award

A recent MBZUAI master’s graduate in computer vision now pursuing his Ph.D., Ahmed Elhagry, is on a mission to share his AI research with a global audience. He was recently recognized in Kyoto, Japan, for his findings on developing more realistic and interactive immersive virtual environments, receiving the Best Ph.D. Forum Paper Award at the IEEE International Conference on Metaverse Computing, Networking and Applications (IEEE MetaCom 2023) in June.

In his paper, “Text-to-Metaverse: Towards a Digital Twin-Enabled Multimodal Conditional Generative Metaverse” authored with his supervisor, Professor Abdulmotaleb El Saddik, Elhagry identified that developing realistic and interactive virtual environments is a major hurdle in the progress of the metaverse. At present, the majority of metaverse applications necessitate the manual construction of 3D models, which is both time-consuming and costly. Additionally, it is challenging to design environments that can promptly react to users’ actions.

To address this challenge, Elhagry and Professor El Saddik’s research proposes a novel approach to generate virtual worlds using digital twin (DT) technology and AI through a text-to-metaverse pipeline. It aims to use multimodal AI and DT technology to produce realistic and highly detailed virtual environments. This approach can benefit industries including education, training, architecture, healthcare, and entertainment, and could change the way that designers and developers create virtual worlds by providing a new direction for creating immersive virtual experiences.

Acknowledging the many contributions that MBZUAI as a research environment made to his award-winning paper, Elhagry said: “The guidance of Professor El Saddik, one of the most renowned scientists and authors in this field, was invaluable to me in this research process and creating the paper. The university’s computational resources were also critical to our work, because these sorts of projects require vast, intense computations to be successful.”

The stated IEEE criteria for Elhagry’s paper to be recognized as the best among his peers included the maturity of his proposed solution to creating more immersive virtual environments, its likely impact on the research community and industry, and its potential for further development.

Following the Kyoto award, Ahmed is not resting on his laurels; he has had two further papers accepted at the top conferences in robotics and automation. The IEEE International Conference on Robotics and Automation (ICRA) in London accepted his research findings on developing a UAV-based perception in complex scenarios that is robust with high accuracy, real-time with fast inference, and sufficiently light-weight to be applicable in resource-constrained embedded devices.  In addition, he is presenting his research on bridging the geometrical perception gap for a cost-efficient and robust perception of the 3D real world in autonomous driving at the IEEE International Conference on Intelligent Robots and Systems (IROS) in Detroit, United States.

One of Elhagry’s reasons for attending MBZUAI as both a master’s and Ph.D. student is the range of AI research topics that the university enables him to pursue, in line with his interests. Ultimately, he plans to build a career in research and development, in which his considerable scientific skills in AI could be applied to real-life industry challenges in a range of industry sectors.