Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,140 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+  - en
+tags:
+  - mast3r
+  - dune
+  - dust3r
+  - 3d-vision
+  - stereo-matching
+  - depth-estimation
+  - point-cloud
+  - sfm
+  - slam
+  - robotics
+pipeline_tag: depth-estimation
+library_name: mast3r-runtime
+---
+
+# MASt3R & DUNE Checkpoints (SafeTensors)
+
+Pre-trained checkpoints for **MASt3R** (Matching And Stereo 3D Reconstruction) and **DUNE** (Dense UNconstrained Estimation) models, converted to SafeTensors format for efficient C++/embedded inference.
+
+## Models
+
+| Model | Resolution | Encoder | Size | Use Case |
+|-------|------------|---------|------|----------|
+| `dune_vit_small_336` | 336x336 | ViT-S/14 | ~1.3 GB | Real-time drone/embedded |
+| `dune_vit_small_448` | 448x448 | ViT-S/14 | ~1.3 GB | Fast inference |
+| `dune_vit_base_336` | 336x336 | ViT-B/14 | ~1.7 GB | Balanced speed/quality |
+| `dune_vit_base_448` | 448x448 | ViT-B/14 | ~1.7 GB | High quality |
+| `mast3r_vit_large` | 512x512 | ViT-L/14 | ~2.9 GB | Maximum precision |
+
+## Architecture
+
+- **Encoder**: DINOv2-based Vision Transformer (DUNE-trained)
+- **Decoder**: MASt3R decoder with CatMLP+DPT heads
+- **Outputs**: Dense 3D points + descriptors for matching
+
+```
+Image Pair → DUNE Encoder → MASt3R Decoder → 3D Points + Descriptors
+```
+
+## Usage
+
+### With mast3r-runtime (recommended)
+
+```bash
+pip install mast3r-runtime
+
+# Download and convert
+mast3r-runtime download dune_vit_small_336
+mast3r-runtime convert dune_vit_small_336 --dtype fp16
+```
+
+### Direct download
+
+```python
+from huggingface_hub import hf_hub_download
+
+# Download encoder
+encoder = hf_hub_download(
+    repo_id="aedelon/mast3r-checkpoints",
+    filename="dune_vit_small_336/encoder.safetensors"
+)
+
+# Download decoder
+decoder = hf_hub_download(
+    repo_id="aedelon/mast3r-checkpoints",
+    filename="dune_vit_small_336/decoder.safetensors"
+)
+```
+
+## Credits & Acknowledgments
+
+These models are converted from the original checkpoints released by **Naver Labs Europe**.
+
+### MASt3R
+> **Grounding Image Matching in 3D with MASt3R**
+> Vincent Leroy, Yohann Cabon, Jérôme Revaud
+> arXiv 2024
+
+```bibtex
+@article{leroy2024mast3r,
+  title={Grounding Image Matching in 3D with MASt3R},
+  author={Leroy, Vincent and Cabon, Yohann and Revaud, J{\'e}r{\^o}me},
+  journal={arXiv preprint arXiv:2406.09756},
+  year={2024}
+}
+```
+
+### DUNE
+> **DUNE: Dense UNconstrained Estimation for 3D Vision**
+> Vincent Leroy, Yohann Cabon, Jérôme Revaud
+> CVPR 2025
+
+```bibtex
+@inproceedings{leroy2025dune,
+  title={DUNE: Dense UNconstrained Estimation for 3D Vision},
+  author={Leroy, Vincent and Cabon, Yohann and Revaud, J{\'e}r{\^o}me},
+  booktitle={CVPR},
+  year={2025}
+}
+```
+
+### DUSt3R
+> **DUSt3R: Geometric 3D Vision Made Easy**
+> Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jérôme Revaud
+> CVPR 2024
+
+```bibtex
+@inproceedings{wang2024dust3r,
+  title={DUSt3R: Geometric 3D Vision Made Easy},
+  author={Wang, Shuzhe and Leroy, Vincent and Cabon, Yohann and Chidlovskii, Boris and Revaud, J{\'e}r{\^o}me},
+  booktitle={CVPR},
+  year={2024}
+}
+```
+
+## Original Repositories
+
+- [naver/mast3r](https://github.com/naver/mast3r) - MASt3R official implementation
+- [naver/dune](https://github.com/naver/dune) - DUNE official implementation
+- [naver/dust3r](https://github.com/naver/dust3r) - DUSt3R official implementation
+
+## License
+
+The model weights are released under **CC BY-NC-SA 4.0** (Creative Commons Attribution-NonCommercial-ShareAlike 4.0).
+
+- **Attribution**: Credit Naver Labs Europe
+- **NonCommercial**: No commercial use without permission
+- **ShareAlike**: Derivatives must use same license
+
+For commercial licensing, contact [Naver Labs Europe](https://europe.naverlabs.com/).
+
+## Converted by
+
+[Delanoe Pirard / Aedelon](https://github.com/aedelon) - [mast3r-runtime](https://github.com/aedelon/mast3r-runtime)
+
+SafeTensors conversion for embedded/C++ inference (Apache 2.0 for runtime code).