Improve model card: Add metadata, links, and updated citation

This PR significantly enhances the model card for GeoSVR by:
- Adding the `pipeline_tag: image-to-3d` for improved discoverability and categorization.
- Specifying the `license: apache-2.0`.
- Updating the main title to match the paper title.
- Providing direct links to the Hugging Face paper page ([GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction](https://huggingface.co/papers/2509.18090)), the official project page ([https://fictionarry.github.io/GeoSVR-project/](https://fictionarry.github.io/GeoSVR-project/)), and the GitHub repository ([https://github.com/Fictionarry/GeoSVR](https://github.com/Fictionarry/GeoSVR)).
- Updating the BibTeX citation to reflect the NeurIPS 2025 acceptance.

Please review these additions and merge if they look good.

README.md

@@ -1,17 +1,27 @@
 ---
-{}
+pipeline_tag: image-to-3d
+license: apache-2.0
 ---
-# Reconstruction on Tanks and Temples and DTU Datasets
+
+# GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
+
+This repository provides the reconstructed meshes and resources for the paper [GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction](https://huggingface.co/papers/2509.18090), which presents an explicit voxel-based framework for accurate, detailed, and complete surface reconstruction.
+
+*   [\ud83d\udcda Paper](https://huggingface.co/papers/2509.18090)
+*   [\ud83c\udf10 Project Page](https://fictionarry.github.io/GeoSVR-project/)
+*   [\ud83d\udcbb Code](https://github.com/Fictionarry/GeoSVR)
+
+## Reconstruction on Tanks and Temples and DTU Datasets
 
 Here we provide the reconstructed meshes of the paper's experiments from GeoSVR.
 
 You can browse all the released meshes at:
 
-- `meshes_complete/`: The complete meshes of the two datasets.
+-   `meshes_complete/`: The complete meshes of the two datasets.
 
-- `DTU_meshes_eval/`: The meshes on DTU datasets, with strict filtering strategy for evaluation.
+-   `DTU_meshes_eval/`: The meshes on DTU datasets, with strict filtering strategy for evaluation.
 
-- `TnT_meshes_eval/`: The meshes on TnT datasets, with strict filtering strategy for evaluation.
+-   `TnT_meshes_eval/`: The meshes on TnT datasets, with strict filtering strategy for evaluation.
 
 Metrics shall be reproduced with the results with postfix of `_eval`.
 
@@ -23,12 +33,12 @@ snapshot_download(repo_id="Fictionary/GeoSVR", cache_dir='./GeoSVR/results', loc
 ```
 or use Git to clone this repository with LFS.
 
-## BibTex
-```
+## Citation
+```bibtex
 @article{li2025geosvr,
   title={GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction},
   author={Li, Jiahe and Zhang, Jiawei and Zhang, Youmin and Bai, Xiao and Zheng, Jin and Yu, Xiaohan and Gu, Lin},
-  journal={arXiv preprint arXiv:2509.18090},
+  journal={Advances in Neural Information Processing Systems},
   year={2025}
 }
 ```