{"ID":2882487,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10894","arxiv_id":"2508.10894","title":"MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data","abstract":"Self-supervised learning holds great promise for remote sensing, but standard self-supervised methods must be adapted to the unique characteristics of Earth observation data. We take a step in this direction by conducting a comprehensive benchmark of fusion strategies and normalization schemes of reconstruction targets for multimodal, multitemporal, and multispectral Earth observation data. Based on our findings, we introduce MAESTRO, a novel adaptation of the Masked Autoencoder with optimized fusion mechanisms and a normalization scheme that incorporates a spectral prior as a self-supervisory signal. Evaluated on four Earth observation datasets in both intra- and cross-dataset settings, MAESTRO achieves state-of-the-art performance on tasks that strongly rely on multitemporal dynamics, while also remaining competitive on others. Code to reproduce all our experiments is available at https://github.com/ignf/maestro.","short_abstract":"Self-supervised learning holds great promise for remote sensing, but standard self-supervised methods must be adapted to the unique characteristics of Earth observation data. We take a step in this direction by conducting a comprehensive benchmark of fusion strategies and normalization schemes of reconstruction targets...","url_abs":"https://arxiv.org/abs/2508.10894","url_pdf":"https://arxiv.org/pdf/2508.10894v2","authors":"[\"Antoine Labatie\",\"Michael Vaccaro\",\"Nina Lardiere\",\"Anatol Garioud\",\"Nicolas Gonthier\"]","published":"2025-08-14T17:58:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":610897,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882487,"paper_url":"https://arxiv.org/abs/2508.10894","paper_title":"MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data","repo_url":"https://github.com/ignf/maestro","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}