Update README.md

README.md

@@ -6,45 +6,63 @@ tags:
 - depth-estimation
 - computer-vision
 ---
+
 # ORB: Omni-directional Reconstruction Backbone
 
 ![ORB Banner](https://raw.githubusercontent.com/speridlabs/ORB/main/assets/banner.png)
 
-**ORB (Omni-directional Reconstruction Backbone)** is a state-of-the-art 360° panorama depth estimation model that predicts dense, scale-invariant distance from a single equirectangular panorama in an end-to-end manner.
+**ORB** is a 360° panorama depth estimation model that predicts dense distance maps from equirectangular panoramas in a single forward pass.
+
+## Model Description
+
+This model takes a 360° equirectangular panorama (2:1 aspect ratio) as input and outputs a dense depth/distance map at the same resolution. It's designed for:
+
+- **Zero-shot depth estimation** from panoramic images
+- **Scale-invariant predictions** with geometric fidelity
+- **End-to-end processing** without post-processing
 
-## 🎯 Key Features
+## Quick Start
 
-- **360° Depth Estimation**: Predicts dense depth maps from equirectangular panoramas
-- **Scale-Invariant**: Robust distance predictions with geometric fidelity
-- **Zero-Shot Generalization**: Strong performance on unseen data
-- **End-to-End**: Single forward pass for complete panorama depth
-- **Easy Integration**: Simple Python API with HuggingFace support
+```python
+from orb import predict_pano_depth
 
-## 🚀 Quick Start
+# Predict depth from panorama
+distance = predict_pano_depth('panorama.png')
+```
+
+## Model Details
 
-For using the model go to the [ORB GitHub Repository](https://github.com/speridlabs/orb)
+- **Input**: RGB panorama (equirectangular, width = 2 × height)
+- **Output**: Dense depth/distance map (same resolution as input)
+- **Format**: SafeTensors (1.3 GB)
+- **Precision**: FP32 / FP16 supported
+- **Base Architecture**: Built upon [DA²: Depth Anything in Any Direction](https://arxiv.org/abs/2509.26618)
 
-## 📁 Model Files
+## 📖 Full Documentation
 
-- `model.safetensors` - Main model weights (1.3 GB)
-- `README.md` - This file
+For complete installation instructions, advanced usage, API documentation, and examples, please visit:
 
-## 🎓 Citation
+**[github.com/speridlabs/ORB](https://github.com/speridlabs/ORB)**
 
-**ORB is based on DA²: Depth Anything in Any Direction**
+## Citation
 
 ```bibtex
-@article{li2025depth,
-  title={DA $^{2}$: Depth Anything in Any Direction},
-  author={Li, Haodong and Zheng, Wangguangdong and He, Jing and Liu, Yuhao and Lin, Xin and Yang, Xin and Chen, Ying-Cong and Guo, Chunchao},
-  journal={arXiv preprint arXiv:2509.26618},
-  year={2025}
+@misc{orb2024,
+  title={ORB: Omni-directional Reconstruction Backbone},
+  author={Sperid Labs and Del Pino, Javier and Garabito, Chema and Sanchez, Alejandro},
+  year={2024},
+  publisher={Sperid Labs},
+  url={https://github.com/speridlabs/ORB}
 }
 ```
 
-## 📜 License
+## License
+
+Apache 2.0 - See [LICENSE](https://github.com/speridlabs/ORB/blob/main/LICENSE)
+
+## Acknowledgements
 
-Apache 2.0 License - See [LICENSE](https://github.com/speridlabs/ORB/blob/main/LICENSE) for details.
+Built upon the foundational work of the [DA-2](https://arxiv.org/abs/2509.26618).
 
 ---