Update pipeline tag to depth-estimation

This PR updates the `pipeline_tag` from `image-to-image` to `depth-estimation`.

While this specific checkpoint focuses on panoramic surface-normal estimation, `depth-estimation` is the standard category on the Hugging Face Hub for 3D geometry reconstruction and depth-related tasks. This change ensures the model is correctly indexed and more discoverable for users interested in panoramic vision and 3D foundation models.

README.md

@@ -1,5 +1,6 @@
 ---
 license: cc-by-nc-4.0
+pipeline_tag: depth-estimation
 tags:
 - surface-normals
 - normal-estimation
@@ -9,7 +10,6 @@ tags:
 - computer-vision
 - in-the-wild
 - zero-shot
-pipeline_tag: image-to-image
 ---
 
 <h1 align="center"> 📟 PaGeR-Normals Model Card</h1>
@@ -32,9 +32,9 @@ pipeline_tag: image-to-image
 </a>
 </p>
 
-`PaGeR-Normals` is the **normals-only** variant of PaGeR released with our paper:
+`PaGeR-Normals` is the **normals-only** variant of PaGeR released with the paper:
 
-- **Paper:** *Unified Panoramic Geometry Estimation via Multi-View Foundation Models* — [arXiv:2605.26368](https://arxiv.org/abs/2605.26368)
+- **Paper:** [Unified Panoramic Geometry Estimation via Multi-View Foundation Models](https://huggingface.co/papers/2605.26368) — [arXiv:2605.26368](https://arxiv.org/abs/2605.26368)
 
 From a single equirectangular (ERP) panorama, it produces a **dense surface-normal map** (unit vectors in the panorama's world frame) in a single forward pass. If you want depth, metric scale, and sky masking from the same model, use the unified [`prs-eth/PaGeR`](https://huggingface.co/prs-eth/PaGeR) checkpoint instead.
 
@@ -120,4 +120,4 @@ If you use this checkpoint in your work, please cite:
   journal = {arXiv preprint arXiv:2605.26368},
   year    = {2026}
 }
-```
+```