Dates: 2023
Principal Investigator: Dr. Saeed Anwar
Funded by: SDAIA-KFUPM Joint Research Center for Artificial Intelligence

Description: This research explores cross-view image transformation, specifically generating street-level scenes from satellite imagery. While satellite images provide broad coverage, street views add localized details like building facades, enhancing geographic localization for applications in robotics, augmented reality, and urban representation. The study proposes a novel transformer-based deep learning approach that leverages attention mechanisms to synthesize coherent, detailed, and geometrically consistent street views from satellite data. This method advances the accuracy and richness of urban imagery, addressing limitations of satellite-only perspectives.