Search papers, labs, and topics across Lattice.
The paper introduces Geo2Sound, a framework for generating realistic soundscapes from satellite imagery by integrating geospatial attributes, semantic hypothesis expansion, and geo-acoustic alignment. To overcome the challenges of semantic ambiguity in top-down satellite views, the framework classifies scenes into geographic attributes, generates diverse sound candidates, and aligns these candidates with acoustic embeddings. The authors also introduce SatSound-Bench, a new benchmark dataset of 20k paired satellite images, text descriptions, and audio recordings, and demonstrate that Geo2Sound achieves a state-of-the-art FAD score of 1.765, significantly outperforming existing methods.
Generate realistic soundscapes from satellite images with 50% better fidelity than existing methods, opening up new possibilities for large-scale environmental monitoring and immersive experiences.
Recent image-to-audio models have shown impressive performance on object-centric visual scenes. However, their application to satellite imagery remains limited by the complex, wide-area semantic ambiguity of top-down views. While satellite imagery provides a uniquely scalable source for global soundscape generation, matching these views to real acoustic environments with unique spatial structures is inherently difficult. To address this challenge, we introduce Geo2Sound, a novel task and framework for generating geographically realistic soundscapes from satellite imagery. Specifically, Geo2Sound combines structural geospatial attributes modeling, semantic hypothesis expansion, and geo-acoustic alignment in a unified framework. A lightweight classifier summarizes overhead scenes into compact geographic attributes, multiple sound-oriented semantic hypotheses are used to generate diverse acoustically plausible candidates, and a geo-acoustic alignment module projects geographic attributes into the acoustic embedding space and identifies the candidate most consistent with the candidate sets. Moreover, we establish SatSound-Bench, the first benchmark comprising over 20k high-quality paired satellite images, text descriptions, and real-world audio recordings, collected from the field across more than 10 countries and complemented by three public datasets. Experiments show that Geo2Sound achieves a SOTA FAD of 1.765, outperforming the strongest baseline by 50.0%. Human evaluations further confirm substantial gains in both realism (26.5%) and semantic alignment, validating our high-fidelity synthesis on scale. Project page and source code: https://github.com/Blanketzzz/Geo2Sound
