Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,9 @@ tags:
|
|
| 13 |
<div align="center">
|
| 14 |
<a href="https://arxiv.org/abs/2508.14475"><img src="https://img.shields.io/badge/Arxiv-preprint-red"></a>
|
| 15 |
<a href="https://pxf0429.github.io/FGResQ/"><img src="https://img.shields.io/badge/Homepage-green"></a>
|
| 16 |
-
<a href=
|
|
|
|
|
|
|
| 17 |
</div>
|
| 18 |
|
| 19 |
<h1 align="center">Fine-grained Image Quality Assessment for Perceptual Image Restoration</h1>
|
|
@@ -42,6 +44,9 @@ tags:
|
|
| 42 |
<div style="font-family: sans-serif; margin-bottom: 2em;">
|
| 43 |
<h2 style="border-bottom: 1px solid #eaecef; padding-bottom: 0.3em; margin-bottom: 1em;">π° News</h2>
|
| 44 |
<ul style="list-style-type: none; padding-left: 0;">
|
|
|
|
|
|
|
|
|
|
| 45 |
<li style="margin-bottom: 0.8em;">
|
| 46 |
<strong>[2025-11-08]</strong> πππOur paper, "Fine-grained Image Quality Assessment for Perceptual Image Restoration", has been accepted to appear at AAAI 2026!
|
| 47 |
</li>
|
|
@@ -68,6 +73,8 @@ pip install -r requirements.txt
|
|
| 68 |
|
| 69 |
### 2. Download Pre-trained Weights
|
| 70 |
|
|
|
|
|
|
|
| 71 |
|
| 72 |
Place the downloaded files in the `weights` directory.
|
| 73 |
|
|
@@ -101,6 +108,13 @@ from model.FGResQ import FGResQ
|
|
| 101 |
# Path to the main model weights
|
| 102 |
model_path = "weights/FGResQ.pth"
|
| 103 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
# Initialize the inference engine
|
| 105 |
model = FGResQ(model_path=model_path)
|
| 106 |
```
|
|
@@ -143,4 +157,4 @@ If you find this work is useful, pleaes cite our paper!
|
|
| 143 |
author={Sheng, Xiangfei and Pan, Xiaofeng and Yang, Zhichao and Chen, Pengfei and Li, Leida},
|
| 144 |
journal={arXiv preprint arXiv:2508.14475},
|
| 145 |
year={2025}
|
| 146 |
-
}
|
|
|
|
| 13 |
<div align="center">
|
| 14 |
<a href="https://arxiv.org/abs/2508.14475"><img src="https://img.shields.io/badge/Arxiv-preprint-red"></a>
|
| 15 |
<a href="https://pxf0429.github.io/FGResQ/"><img src="https://img.shields.io/badge/Homepage-green"></a>
|
| 16 |
+
<a href="https://huggingface.co/spaces/orpheus0429/FGResQ"><img src="https://img.shields.io/badge/π€%20Hugging%20Face-Spaces-blue"></a>
|
| 17 |
+
<a href='https://github.com/sxfly99/FGResQ/stargazers'><img src='https://img.shields.io/github/stars/sxfly99/FGResQ.svg?style=social'></a>
|
| 18 |
+
|
| 19 |
</div>
|
| 20 |
|
| 21 |
<h1 align="center">Fine-grained Image Quality Assessment for Perceptual Image Restoration</h1>
|
|
|
|
| 44 |
<div style="font-family: sans-serif; margin-bottom: 2em;">
|
| 45 |
<h2 style="border-bottom: 1px solid #eaecef; padding-bottom: 0.3em; margin-bottom: 1em;">π° News</h2>
|
| 46 |
<ul style="list-style-type: none; padding-left: 0;">
|
| 47 |
+
<li style="margin-bottom: 0.8em;">
|
| 48 |
+
<strong>[2025-11-19]</strong> The model is now available on the <a href="https://huggingface.co/orpheus0429/FGResQ">HuggingFace Hub</a>. A live demo is also available on <a href="https://huggingface.co/spaces/orpheus0429/FGResQ">HuggingFace Spaces</a> for you to try it out directly in your browser.
|
| 49 |
+
</li>
|
| 50 |
<li style="margin-bottom: 0.8em;">
|
| 51 |
<strong>[2025-11-08]</strong> πππOur paper, "Fine-grained Image Quality Assessment for Perceptual Image Restoration", has been accepted to appear at AAAI 2026!
|
| 52 |
</li>
|
|
|
|
| 73 |
|
| 74 |
### 2. Download Pre-trained Weights
|
| 75 |
|
| 76 |
+
You can download the pre-trained model weights from the following link:
|
| 77 |
+
[**Download Weights (Google Drive)**](https://drive.google.com/drive/folders/10MVnAoEIDZ08Rek4qkStGDY0qLiWUahJ?usp=drive_link), [**(Baidu Netdisk)**](https://pan.baidu.com/s/1a2IZbr_PrgZYCbUbjKLykA?pwd=9ivu) or [**(HuggingFace)**](https://huggingface.co/orpheus0429/FGResQ)
|
| 78 |
|
| 79 |
Place the downloaded files in the `weights` directory.
|
| 80 |
|
|
|
|
| 108 |
# Path to the main model weights
|
| 109 |
model_path = "weights/FGResQ.pth"
|
| 110 |
|
| 111 |
+
# or use HuggingFace Model
|
| 112 |
+
# from huggingface_hub import hf_hub_download
|
| 113 |
+
# model_path = hf_hub_download(
|
| 114 |
+
# repo_id="orpheus0429/FGResQ",
|
| 115 |
+
# filename="weights/FGResQ.pth"
|
| 116 |
+
# )
|
| 117 |
+
|
| 118 |
# Initialize the inference engine
|
| 119 |
model = FGResQ(model_path=model_path)
|
| 120 |
```
|
|
|
|
| 157 |
author={Sheng, Xiangfei and Pan, Xiaofeng and Yang, Zhichao and Chen, Pengfei and Li, Leida},
|
| 158 |
journal={arXiv preprint arXiv:2508.14475},
|
| 159 |
year={2025}
|
| 160 |
+
}
|