Add pipeline tag and improve metadata

Hi! I'm Niels from the community science team at Hugging Face.

This PR adds the `pipeline_tag: image-to-3d` to the model card metadata. This helps categorize the model correctly on the Hugging Face Hub and makes it easier for the community to discover your work in the 3D reconstruction and video processing space.

README.md

@@ -1,4 +1,5 @@
 ---
+pipeline_tag: image-to-3d
 tags:
 - computer-vision
 - 3d-reconstruction
@@ -7,7 +8,7 @@ tags:
 
 # LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
 
-This repository contains the reimplemented model checkpoints for **LoGeR**. 
+This repository contains the reimplemented model checkpoints for **LoGeR**, as presented in the paper [LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory](https://huggingface.co/papers/2603.03269). 
 
 LoGeR processes long video streams in chunks with a hybrid memory design to improve large-scale geometric reconstruction quality and consistency.
 
@@ -35,7 +36,7 @@ You can download the weights directly via `wget`:
 wget -O ckpts/LoGeR/latest.pt https://huggingface.co/Junyi42/LoGeR/resolve/main/LoGeR/latest.pt?download=true
 
 # Download LoGeR_star
-wget -O ckpts/LoGeR_star/latest.pt https://huggingface.co/Junyi42/LoGeR/resolve/main/LoGeR_star/latest.pt?download=true
+wget -O ckpts/LoGeR_star/latest.pt https://huggingface.co/Junyi42/LoGeR_star/latest.pt?download=true
 ```
 
 ## Usage
@@ -51,4 +52,4 @@ If you find our work or these models useful, please cite our paper:
   journal={arXiv preprint arXiv:2603.03269},
   year={2026}
 }
-```
+```