Add image-to-image pipeline tag and link to paper

This PR adds the `pipeline_tag: image-to-image` to the model card metadata. This will allow the model to be properly categorized and discovered on the Hugging Face Model Hub. Also adding a direct link to the paper.

README.md

@@ -1,14 +1,16 @@
 ---
+license: mit
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
 - renderformer
-license: mit
+pipeline_tag: image-to-image
 ---
 
 # RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination</h1>
 
-This repo contains the weights of **RenderFormer-V1.1-Large**.
+This repo contains the weights of **RenderFormer-V1.1-Large**.\
+For more information, see [the paper](https://huggingface.co/papers/2505.21925).
 
 ## Quick Start