Hugging Face's logo
Mikolaj Czerkawski's picture
18 3 25

Mikolaj Czerkawski

mikonvergence
aliFrancis's profile picture Tonic's profile picture 21world's profile picture
Ā·
https://mikonvergence.github.io

AI & ML interests

None yet

Recent Activity

replied to their post 2 days ago
šŸ”µ š‚šŽš-š†š„š-ššžš­šš: š”š§š¢šŸš¢šžš š†šžš§šžš«ššš­š¢šÆšž šŒšØššžš„š„š¢š§š  šØšŸ š‚šŽššžš«š§š¢šœš®š¬ šˆš¦ššš šžš«š² š“š”š®š¦š›š§ššš¢š„š¬ Today we release a prototype of COP-GEN - a universal generative model for Copernicus data. š‚šŽš-š†š„š-ššžš­šš is a model trained globally on the thumbnails of the Major TOM Core datasets, including Sentinel-2 L1C, Sentinel-2 L2A, Sentinel-1 RTC, and COP-DEM GLO-30. āš–ļø šŒšØššžš„ https://huggingface.co/mespinosami/COP-GEN-Beta šŸ“± šƒšžš¦šØ https://huggingface.co/spaces/mikonvergence/COP-GEN-Beta How is it universal? COP-GEN learns a joint generative process of all modalities, which means that it can reconstruct data from any subset of present observations. š–š¢š­š”šØš®š­ š­š«ššš¢š§š¢š§š  š¬š©šžšœš¢šŸš¢šœššš„š„š² to perform any of these tasks it can be used to approximate: āœ… Sentinel-1 to Sentinel-2 translation āœ… Elevation estimation from Sentinel-2 or Sentinel-1 āœ… Atmospheric Correction (L1C to L2A pipeline) āœ… Atmospheric Generation (L2A to L1C) āœ… ...and any other task involving translation between the supported modalities On its own, the model can be used as a useful prior for estimating the data likelihood distribution for Copernicus data. COP-GEN-Beta learns joint, conditional, and marginal distributions within a single unified backbone, allowing to flexibly sample any modality given any condition. Why is it Beta? Because thumbnails are a low-cost representation of the data that scales well and we managed to develop this prototype quite fast. We are currently developing the more costly COP-GEN model that supports the original data. For now, we wanted to showcase the prototype and make it available to the community for a test! šŸŒ š–šžš›š¬š¢š­šž https://miquel-espinosa.github.io/cop-gen šŸ’» š‚šØššž https://github.com/miquel-espinosa/COP-GEN-Beta šŸ“„ šššš©šžš« https://arxiv.org/pdf/2504.08548
posted an update 2 days ago
šŸ”µ š‚šŽš-š†š„š-ššžš­šš: š”š§š¢šŸš¢šžš š†šžš§šžš«ššš­š¢šÆšž šŒšØššžš„š„š¢š§š  šØšŸ š‚šŽššžš«š§š¢šœš®š¬ šˆš¦ššš šžš«š² š“š”š®š¦š›š§ššš¢š„š¬ Today we release a prototype of COP-GEN - a universal generative model for Copernicus data. š‚šŽš-š†š„š-ššžš­šš is a model trained globally on the thumbnails of the Major TOM Core datasets, including Sentinel-2 L1C, Sentinel-2 L2A, Sentinel-1 RTC, and COP-DEM GLO-30. āš–ļø šŒšØššžš„ https://huggingface.co/mespinosami/COP-GEN-Beta šŸ“± šƒšžš¦šØ https://huggingface.co/spaces/mikonvergence/COP-GEN-Beta How is it universal? COP-GEN learns a joint generative process of all modalities, which means that it can reconstruct data from any subset of present observations. š–š¢š­š”šØš®š­ š­š«ššš¢š§š¢š§š  š¬š©šžšœš¢šŸš¢šœššš„š„š² to perform any of these tasks it can be used to approximate: āœ… Sentinel-1 to Sentinel-2 translation āœ… Elevation estimation from Sentinel-2 or Sentinel-1 āœ… Atmospheric Correction (L1C to L2A pipeline) āœ… Atmospheric Generation (L2A to L1C) āœ… ...and any other task involving translation between the supported modalities On its own, the model can be used as a useful prior for estimating the data likelihood distribution for Copernicus data. COP-GEN-Beta learns joint, conditional, and marginal distributions within a single unified backbone, allowing to flexibly sample any modality given any condition. Why is it Beta? Because thumbnails are a low-cost representation of the data that scales well and we managed to develop this prototype quite fast. We are currently developing the more costly COP-GEN model that supports the original data. For now, we wanted to showcase the prototype and make it available to the community for a test! šŸŒ š–šžš›š¬š¢š­šž https://miquel-espinosa.github.io/cop-gen šŸ’» š‚šØššž https://github.com/miquel-espinosa/COP-GEN-Beta šŸ“„ šššš©šžš« https://arxiv.org/pdf/2504.08548
liked a model 3 days ago
mespinosami/COP-GEN-Beta
View all activity

Organizations

Gradio-Themes-Party's profile picture satellite-image-deep-learning's profile picture European Space Agency Ī¦-lab's profile picture Major TOM's profile picture Hugging Face Discord Community's profile picture

mikonvergence's activity

liked a model 3 days ago
liked a Space 4 days ago
liked a Space 7 days ago
liked a model 7 days ago
liked 4 datasets 5 months ago
liked a dataset 6 months ago
liked 2 datasets 8 months ago
liked a dataset 12 months ago
liked a Space 12 months ago
liked a dataset about 1 year ago
liked 3 Spaces about 1 year ago
liked 2 datasets about 1 year ago
liked a dataset over 1 year ago