COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913794340421632 |
|---|---|
| author | Espinosa, Miguel Marsocci, Valerio Jia, Yuru Crowley, Elliot J. Czerkawski, Mikolaj |
| author_facet | Espinosa, Miguel Marsocci, Valerio Jia, Yuru Crowley, Elliot J. Czerkawski, Mikolaj |
| contents | 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 significant challenge. Traditional methods have often been limited to single or dual-modality approaches. In this paper, we introduce COP-GEN-Beta, a generative diffusion model trained on optical, radar, and elevation data from the Major TOM dataset. What sets COP-GEN-Beta apart is its ability to map any subset of modalities to any other, enabling zero-shot modality translation after training. This is achieved through a sequence-based diffusion transformer, where each modality is controlled by its own timestep embedding. We extensively evaluate COP-GEN-Beta on thumbnail images from the Major TOM dataset, demonstrating its effectiveness in generating high-quality samples. Qualitative and quantitative evaluations validate the model's performance, highlighting its potential as a powerful pre-trained model for future remote sensing tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08548 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails Espinosa, Miguel Marsocci, Valerio Jia, Yuru Crowley, Elliot J. Czerkawski, Mikolaj Graphics Computer Vision and Pattern Recognition 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 significant challenge. Traditional methods have often been limited to single or dual-modality approaches. In this paper, we introduce COP-GEN-Beta, a generative diffusion model trained on optical, radar, and elevation data from the Major TOM dataset. What sets COP-GEN-Beta apart is its ability to map any subset of modalities to any other, enabling zero-shot modality translation after training. This is achieved through a sequence-based diffusion transformer, where each modality is controlled by its own timestep embedding. We extensively evaluate COP-GEN-Beta on thumbnail images from the Major TOM dataset, demonstrating its effectiveness in generating high-quality samples. Qualitative and quantitative evaluations validate the model's performance, highlighting its potential as a powerful pre-trained model for future remote sensing tasks. |
| title | COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.08548 |