Hugging Face's logo

XiangZ
/
hit-sr

Image-to-Image
HiT-SR
image super-resolution
transformer
efficient transformer
Model card Files Community
XiangZ commited on
Commit
26f4236
·
verified ·
1 Parent(s): a57b4a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - HiT-SR
4
  - image super-resolution
@@ -10,7 +11,7 @@ tags:
10
  HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
11
  </h1>
12
 
13
- <h3><a href="https://github.com/XiangZ-0/HiT-SR">[Github]</a> | <a href="https://1drv.ms/b/c/de821e161e64ce08/EVsrOr1-PFFMsXxiRHEmKeoBSH6DPkTuN2GRmEYsl9bvDQ?e=f9wGUO">[Paper]</a> | <a href="https://1drv.ms/b/c/de821e161e64ce08/EYmRy-QOjPdFsMRT_ElKQqABYzoIIfDtkt9hofZ5YY_GjQ?e=2Iapqf">[Supp]</a> | <a href="https://www.youtube.com/watch?v=9rO0pjmmjZg">[Video]</a> | <a href="https://1drv.ms/f/c/de821e161e64ce08/EuE6xW-sN-hFgkIa6J-Y8gkB9b4vDQZQ01r1ZP1lmzM0vQ?e=aIRfCQ">[Visual Results]</a> </h3>
14
  <div></div>
15
 
16
  HiT-SR is a general strategy to improve transformer-based SR methods. We apply our HiT-SR approach to improve [SwinIR-Light](https://github.com/JingyunLiang/SwinIR), [SwinIR-NG](https://github.com/rami0205/NGramSwin) and [SRFormer-Light](https://github.com/HVision-NKU/SRFormer), corresponding to our HiT-SIR, HiT-SNG, and HiT-SRF. Compared with the original structure, our improved models achieve better SR performance while reducing computational burdens.
 
1
  ---
2
+ pipeline_tag: image-to-image
3
  tags:
4
  - HiT-SR
5
  - image super-resolution
 
11
  HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
12
  </h1>
13
 
14
+ <h3><a href="https://github.com/XiangZ-0/HiT-SR">[Github]</a> | <a href="https://huggingface.co/papers/2407.05878">[Paper]</a> | <a href="https://1drv.ms/b/c/de821e161e64ce08/EYmRy-QOjPdFsMRT_ElKQqABYzoIIfDtkt9hofZ5YY_GjQ?e=2Iapqf">[Supp]</a> | <a href="https://www.youtube.com/watch?v=9rO0pjmmjZg">[Video]</a> | <a href="https://1drv.ms/f/c/de821e161e64ce08/EuE6xW-sN-hFgkIa6J-Y8gkB9b4vDQZQ01r1ZP1lmzM0vQ?e=aIRfCQ">[Visual Results]</a> </h3>
15
  <div></div>
16
 
17
  HiT-SR is a general strategy to improve transformer-based SR methods. We apply our HiT-SR approach to improve [SwinIR-Light](https://github.com/JingyunLiang/SwinIR), [SwinIR-NG](https://github.com/rami0205/NGramSwin) and [SRFormer-Light](https://github.com/HVision-NKU/SRFormer), corresponding to our HiT-SIR, HiT-SNG, and HiT-SRF. Compared with the original structure, our improved models achieve better SR performance while reducing computational burdens.