Commit
•
b22e9c8
1
Parent(s):
d0ecf3b
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
# [CVPR2024 Oral] Image Processing GNN: Breaking Rigidity in Super-Resolution
|
| 5 |
+
|
| 6 |
+
<p align="left">
|
| 7 |
+
<a href="https://openaccess.thecvf.com/content/CVPR2024/papers/Tian_Image_Processing_GNN_Breaking_Rigidity_in_Super-Resolution_CVPR_2024_paper.pdf" alt="arXiv">
|
| 8 |
+
Paper</a> |
|
| 9 |
+
<a href="https://ipgnn.github.io" alt="arXiv">
|
| 10 |
+
Project Page</a> |
|
| 11 |
+
<a href="https://openaccess.thecvf.com/content/CVPR2024/html/Tian_Image_Processing_GNN_Breaking_Rigidity_in_Super-Resolution_CVPR_2024_paper.html" alt="arXiv">
|
| 12 |
+
<img src="https://img.shields.io/badge/CVPR'24-Oral-b31b31b.svg?style=flat" /></a>
|
| 13 |
+
<a href="https://huggingface.co/yuchuantian/IPG/tree/main" alt="Hugging Face Models">
|
| 14 |
+
<img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue" /></a>
|
| 15 |
+
</p>
|
| 16 |
+
This is the official repo of our CVPR'24 paper **Image Processing GNN: Breaking Rigidity in Super-Resolution**. In the paper, we propose IPG: a Graph-based SR model that achieves outstanding performance on various SR benchmarks.
|
| 17 |
+
|
| 18 |
+
## News
|
| 19 |
+
|
| 20 |
+
7/6/2024: We opensourced the code & weights of IPG!
|
| 21 |
+
|
| 22 |
+
6/19/2024: Our work got the **Best Student Runner-up Award** of CVPR'24!🎉🎉
|
| 23 |
+
|
| 24 |
+
6/2/2024: We open-sourced [U-DiT](https://github.com/YuchuanTian/U-DiT), an efficient U-Net-style DiT variant.
|
| 25 |
+
|
| 26 |
+
## Replication
|
| 27 |
+
|
| 28 |
+
| Model | Scale | Urban100 | Weights |
|
| 29 |
+
| ----- | ----- | -------- | ------------------------------------------------------------ |
|
| 30 |
+
| GRL-B | 2x | 33.97 | [🤗Link](https://huggingface.co/yuchuantian/IPG_rep/tree/main/GRLB_2_shbj1_676) |
|
| 31 |
+
| GRL-B | 3x | 29.83 | [🤗Link](https://huggingface.co/yuchuantian/IPG_rep/tree/main/GRLB_3_shbj4_81) |
|
| 32 |
+
| GRL-B | 4x | 27.53 | [🤗Link](https://huggingface.co/yuchuantian/IPG_rep/tree/main/GRLB_4_shbj4_68) |
|
| 33 |
+
| HAT | 2x | 34.45 | [🤗Link](https://huggingface.co/yuchuantian/IPG_rep/tree/main/HAT_2_shbj8_21) |
|
| 34 |
+
|