Create README.md

README.md

@@ -0,0 +1,113 @@
+---
+license: cc-by-4.0
+tags:
+- earth-observation
+- remote-sensing
+- diffusion
+- generative
+- copernicus
+- sentinel
+- major-tom
+- multimodal
+- latent-diffusion
+library_name: cop-gen
+datasets:
+- Major-TOM/COP-GEN-Benchmark
+---
+
+![copgen-banner-github](https://cdn-uploads.huggingface.co/production/uploads/63ea69a55c837d9968ebecc0/M3pNdfNV83ukK2czA2M-1.png)
+
+# COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
+
+[![arXiv](https://img.shields.io/badge/arXiv-2603.03239-D12424)](https://arxiv.org/abs/2603.03239)
+[![GitHub](https://img.shields.io/badge/GitHub-COP--GEN-black?logo=github)](https://github.com/miquel-espinosa/COP-GEN)
+[![Website](https://img.shields.io/badge/🌐-Website-grey)](https://miquel-espinosa.github.io/cop-gen/)
+[![HF Collection](https://img.shields.io/badge/🤗-Collection-yellow)](https://huggingface.co/collections/mespinosami/copgen)
+
+COP-GEN is a generative foundation model for Copernicus Earth observation data. It learns a joint distribution over all major Copernicus modalities — Sentinel-1 SAR, Sentinel-2 multispectral (L1C and L2A), DEM, and LULC — enabling both unconditional generation and cross-modal conditional synthesis (e.g. generate S2 RGB from S1 SAR, or generate all modalities jointly).
+
+## Model Details
+
+- **Developed by:** Miguel Espinosa, Eva Gmelich Meijling, Valerio Marsocci, Elliot J. Crowley, Mikolaj Czerkawski
+- **Model type:** Latent Diffusion Transformer (multimodal, multi-resolution)
+- **Modalities:** S1RTC (VV, VH), S2L1C (all bands + cloud mask), S2L2A (all bands), DEM, LULC, timestamps, lat-lon
+- **License:** CC-BY-4.0
+- **Paper:** [arXiv:2603.03239](https://arxiv.org/abs/2603.03239)
+- **Repository:** [github.com/miquel-espinosa/COP-GEN](https://github.com/miquel-espinosa/COP-GEN)
+
+### Architecture
+
+COP-GEN operates in a shared latent space produced by a set of modality-specific KL-regularised VAEs. The diffusion backbone is a transformer trained jointly over all modalities, supporting arbitrary conditioning at inference time — any subset of modalities can be held as conditions while the rest are generated.
+
+## Uses
+
+### Direct Use
+
+Generate synthetic Copernicus EO scenes, either unconditionally or conditioned on one or more input modalities. Useful for data augmentation, gap-filling missing modalities, and studying cross-sensor relationships.
+
+### Downstream Use
+
+The latent representations and generated samples can serve as inputs to downstream EO tasks: land cover classification, change detection, cloud removal, SAR-to-optical translation, and more.
+
+## How to Get Started
+
+```python
+from libs.copgen import CopgenModel
+
+model = CopgenModel(
+    model_path="path/to/model_checkpoint.pth",
+    config_path="path/to/model_config.py"
+)
+
+# Conditional generation: provide one or more modalities as conditions
+samples = model.generate(
+    modalities=["S2L2A_B02_B03_B04_B08", "S1RTC_vh_vv"],
+    conditions={"S1RTC_vh_vv": s1_tensor},
+    n_samples=4,
+)
+
+# Unconditional generation
+samples = model.generate(
+    modalities=["S2L2A_B02_B03_B04_B08", "S1RTC_vh_vv"],
+    n_samples=4,
+)
+```
+
+See [examples/conditional_generation.py](https://github.com/miquel-espinosa/COP-GEN/blob/main/examples/conditional_generation.py) and [examples/unconditional_generation.py](https://github.com/miquel-espinosa/COP-GEN/blob/main/examples/unconditional_generation.py) for full worked examples.
+
+## Training Details
+
+### Training Data
+
+Trained on [Major-TOM](https://huggingface.co/Major-TOM) global Copernicus data, covering Sentinel-1 RTC, Sentinel-2 L1C and L2A, DEM, and LULC. A pre-compiled Edinburgh subset is available at [mespinosami/copgen-edinburgh-subset](https://huggingface.co/datasets/mespinosami/copgen-edinburgh-subset) for local development and reproduction.
+
+### Training Procedure
+
+1. Modality-specific KL-VAEs are trained separately per modality and resolution.
+2. All modalities are encoded into a shared latent space.
+3. A diffusion transformer backbone is trained jointly over the merged latents, with random masking of modalities to enable conditional generation at inference.
+
+See the [GitHub README](https://github.com/miquel-espinosa/COP-GEN) for full training instructions.
+
+## Evaluation
+
+Evaluated on the [COP-GEN-Benchmark](https://huggingface.co/datasets/Major-TOM/COP-GEN-Benchmark) test set (495 held-out global scenes). Distribution-level metrics (FID and related) are reported in Table 1 of the paper. To reproduce:
+
+```bash
+pip install -r benchmark/stochastic/requirements.txt
+python -m benchmark.stochastic.run --output metrics.csv
+```
+
+## Citation
+
+```bibtex
+@article{copgen2026,
+    title   = {COP-GEN: Latent Diffusion Transformer for Copernicus Earth
+               Observation Data},
+    author  = {Espinosa, Miguel and Gmelich Meijling, Eva and Marsocci,
+               Valerio and Crowley, Elliot J. and Czerkawski, Mikolaj},
+    year    = {2026},
+    journal = {arXiv preprint arXiv:2603.03239},
+    url     = {https://arxiv.org/abs/2603.03239},
+}
+```