new description

README.md

@@ -9,5 +9,4 @@ license: mit
 suggested_hardware: t4-small
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
-# Port 7860
+This is a demo of the CutS3D zero-shot model from the paper [CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation](https://arxiv.org/abs/2411.16319).

app.py

@@ -7,7 +7,7 @@ import gradio as gr
 from model import run_model
 
 DESCRIPTION = '# [CutS3D](https://leonsick.github.io/cuts3d/): Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation \n\n' \
-                'This is a demo for the CutS3D Zero-Shot model. The model is trained on ImageNet, initially with unsupervised pseudo-masks and then further with one round of self-training. The first prediction will likely be slow as the model is downloaded. Subsequent predictions will be faster. The template for this space was borrowed from the original CutLER space by [hysts](https://huggingface.co/hysts). Read our paper is on [arXiv](arxiv.org/abs/2411.16319).' \
+                'This is a demo for the CutS3D Zero-Shot model. The model is trained on ImageNet, initially with unsupervised pseudo-masks and then further with one round of self-training. The first prediction will likely be slow as the model is downloaded. Subsequent predictions will be faster. The template for this space was borrowed from the original CutLER space by [hysts](https://huggingface.co/hysts).' \
 
 paths = sorted(pathlib.Path('demo_imgs').glob('*.jpg'))