15.06.2025
Xiaoxiang Zhu Receives Best Paper Award at EarthVision Workshop @ CVPR 2025
Advancing Foundation Models for Earth Observation
MCML PI Xiaoxiang Zhu and collaborators received the Best Paper Award at the EarthVision Workshop, held in conjunction with CVPR 2025, for their paper "Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation." The work introduces a foundation model designed to process data from diverse Earth observation sensors within a unified framework.
Panopticon extends foundation models beyond fixed sensor configurations by enabling flexible integration of optical and radar imagery with varying spectral characteristics. By supporting sensor-agnostic learning, the approach improves performance across a wide range of Earth observation tasks and paves the way for more versatile AI systems for environmental monitoring and geospatial analysis.
Related
16.09.2026
Vincent Fortuin Receives ERC Starting Grant for Reliable Small-Data AI
MCML PI Vincent Fortuin receives an ERC Starting Grant for AutoBayes, advancing reliable AI methods for learning from small datasets.
