Update model card with metadata, links and sample usage

Hi! I'm Niels from the community science team at Hugging Face. I've opened this PR to enhance your model card with additional metadata and structured information.

This PR:
- Adds the `image-to-3d` pipeline tag to the metadata for better discoverability.
- Provides a more detailed description of the model and its capabilities.
- Adds links to your project page, research paper, and GitHub repository.
- Includes a sample usage snippet for rendering videos from the `.ply` files.
- Adds visualization instructions for online viewers.
- Includes the official citation.

These changes make it easier for researchers and developers to find and use your work!

README.md

@@ -1,14 +1,54 @@
 ---
-license: apache-2.0
 datasets:
 - jayinnn/Skyfall-GS-datasets
+license: apache-2.0
+pipeline_tag: image-to-3d
 ---
 
-# The fused 3DGS PLY files for Skyfall-GS
+# Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
+
+This repository contains the fused 3D Gaussian Splatting (3DGS) `.ply` files for **Skyfall-GS**, a framework for synthesizing large-scale, immersive 3D urban scenes.
+
+[**Project Page**](https://skyfall-gs.jayinnn.dev/) | [**Paper**](https://huggingface.co/papers/2510.15869) | [**GitHub**](https://github.com/jayin92/skyfall-gs)
+
+## Description
+
+Skyfall-GS is a hybrid framework that synthesizes city-block scale 3D urban scenes by combining satellite reconstruction with diffusion refinement. It leverages readily available satellite imagery to provide realistic coarse geometry and uses open-domain diffusion models to synthesize high-quality close-up appearances. This approach eliminates the need for costly 3D annotations and allows for real-time, immersive 3D exploration.
+
+## Visualization
+
+The `.ply` files in this repository are intended for use with Gaussian Splatting viewers. For the best experience, use a fused PLY file with the following tools:
+
+1.  **Mip-Splatting Viewer**: Use the [online viewer](https://niujinshuchong.github.io/mip-splatting-demo). Recommended settings:
+    - **Up vector:** `0,0,1`
+    - **SH degree:** `1`
+    - **Camera origin:** `0,0,200`
+2.  **SuperSplat**: You can also use the web-based [SuperSplat Editor](https://superspl.at/editor).
+
+## Sample Usage
+
+To render a video from a `.ply` file using the scripts provided in the [official repository](https://github.com/jayin92/skyfall-gs):
+
+```bash
+python render_video_from_ply.py \
+    --ply_path <path_to_ply_file> \
+    --camera_path <path_to_camera.json>
+```
 
-> Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
+## Citation
 
-Check our project page: https://skyfall-gs.jayinnn.dev/
+If you find this work useful, please consider citing:
 
-arXiv link: arxiv.org/abs/2510.15869
+```bibtex
+@article{lee2025SkyfallGS,
+  title = {{Skyfall-GS}: Synthesizing Immersive {3D} Urban Scenes from Satellite Imagery},
+  author = {Jie-Ying Lee and Yi-Ruei Liu and Shr-Ruei Tsai and Wei-Cheng Chang and Chung-Ho Wu and Jiewen Chan and Zhenjun Zhao and Chieh Hubert Lin and Yu-Lun Liu},
+  journal = {arXiv preprint},
+  year = {2025},
+  eprint = {2510.15869},
+  archivePrefix = {arXiv}
+}
+```
 
+## Acknowledgement
+This codebase is built upon several open-source projects: [Mip-Splatting](https://github.com/autonomousvision/mip-splatting), [WildGuassians](https://github.com/jkulhanek/wild-gaussians), [FlowEdit](https://github.com/fallenshock/FlowEdit), [MoGe](https://github.com/microsoft/MoGe), and [SatelliteSfM](https://github.com/Kai-46/SatelliteSfM).