معرفی
Iro Armeni is an Assistant Professor in the Civil and Environmental Engineering Department at Stanford University's School of Engineering. She leads the Gradient Spaces research group, focusing on the intersection of civil engineering, architecture, and machine perception to design and construct data-driven environments across physical and digital space.
Her educational background is highly interdisciplinary: PhD in Civil and Environmental Engineering with Minor in Computer Science from Stanford University (2020), Postdoctoral Researcher at ETH Zurich (2023), MSc in Computer Science from Ionian University (2013), MEng in Architectural Engineering from University of Tokyo (2011), and Diploma in Architectural Engineering from National Technical University of Athens (2009). Before academia, she worked as an architect and consultant for both private and public sectors.
Dr. Armeni's research focuses on developing quantitative and data-driven methods that learn from real-world visual data to generate, predict, and simulate new or renewed built environments with humans at the center. She is particularly interested in creating gradient spaces that blend 100% physical (real reality) to 100% digital (virtual reality) using Mixed Reality. Her work spans computer vision, 3D scene understanding, semantic mapping, and their applications in the built environment.
Her recent publications demonstrate significant contributions across multiple venues including CVPR, ECCV, SIGGRAPH, and ISPRS Journal, with research themes centered around 3D scene understanding, appearance transfer, scene synthesis, SLAM in dynamic environments, and semantic mapping. Her work shows a consistent trajectory toward creating sustainable, inclusive, and adaptive built environments that support current and future physical and digital needs.
She has received prestigious awards including the ETH Zurich Postdoctoral Fellowship, Google PhD Fellowship, and MEXT Scholarship. Her teaching includes graduate courses such as Designing for Gradient Spaces (CEE342), Computer Vision for the Built Environment (CEE247C), and AI Applications in AEC (CEE329), reflecting her interdisciplinary approach to integrating machine perception with civil engineering applications.
