{"ID":2855840,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12670","arxiv_id":"2510.12670","title":"TerraCodec: Compressing Optical Earth Observation Data","abstract":"Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented and lacks publicly available, large-scale pretrained codecs. Moreover, prior work has largely focused on image compression, leaving temporal redundancy and EO video codecs underexplored. To address these gaps, we introduce TerraCodec (TEC), a family of learned codecs pretrained on Sentinel-2 EO data. TEC includes efficient multispectral image variants and a Temporal Transformer model (TEC-TT) that leverages dependencies across time. To overcome the fixed-rate setting of today's neural codecs, we present Latent Repacking, a novel method for training flexible-rate transformer models that operate on varying rate-distortion settings. TerraCodec outperforms classical codecs, achieving 3-10x higher compression at equivalent image quality. Beyond compression, TEC-TT enables zero-shot cloud inpainting, surpassing state-of-the-art methods on the AllClear benchmark. Our results establish neural codecs as a promising direction for Earth observation. Our code and models are publically available at https://github.com/IBM/TerraCodec.","short_abstract":"Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented and lacks publicly available, large-scale pretrained codecs. Moreover, prior work has largely focused on image compression...","url_abs":"https://arxiv.org/abs/2510.12670","url_pdf":"https://arxiv.org/pdf/2510.12670v3","authors":"[\"Julen Costa-Watanabe\",\"Isabelle Wittmann\",\"Benedikt Blumenstiel\",\"Konrad Schindler\"]","published":"2025-10-14T16:05:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":608292,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855840,"paper_url":"https://arxiv.org/abs/2510.12670","paper_title":"TerraCodec: Compressing Optical Earth Observation Data","repo_url":"https://github.com/IBM/TerraCodec","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}