Miguel Antonio M. Sumulong

Semantically-Guided Hydro-Synthesis for Mitigating Severe Inundation Visual Paucity in Vision-Based Urban Flood Monitoring Using Latent Diffusion Models

Results indicate that site-specific, semantically-guided generative augmentation provides a measurable and statistically significant improvement over both raw-data and algorithmic class-imbalance baselines, addressing hydrological data scarcity for vision-based disaster response systems.