9 papers
COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
Miguel Espinosa, Eva Gmelich Meijling, Valerio Marsocci +2
Earth observation applications increasingly rely on data from multiple sensors, including optical, radar, elevation, and land-cover. Relationships between modalities are fundamenta…
EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
Yijie Zheng, Weijie Wu, Bingyue Wu +4
While the Earth observation community has witnessed a surge in high-impact foundation models and global Earth embedding datasets, a significant barrier remains in translating these…
HeatMat: Simulation of City Material Impact on Urban Heat Island Effect
Marie Reinbigler, Romain Rouffet, Peter Naylor +5
The Urban Heat Island (UHI) effect, defined as a significant increase in temperature in urban environments compared to surrounding areas, is difficult to study in real cities using…
TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data
Benedikt Blumenstiel, Paolo Fraccaro, Valerio Marsocci +8
Large-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public da…
COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails
Miguel Espinosa, Valerio Marsocci, Yuru Jia +2
In remote sensing, multi-modal data from various sensors capturing the same scene offers rich opportunities, but learning a unified representation across these modalities remains a…
MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
Paul Borne--Pons, Mikolaj Czerkawski, Rosalie Martin +1
Terrain modeling has traditionally relied on procedural techniques, which often require extensive domain expertise and handcrafted rules. In this paper, we present MESA - a novel d…