Image-to-Image
image-super-resolution
alebeck nielsr HF Staff commited on
Commit
f28a046
·
verified ·
1 Parent(s): 3ab3b68

Improve model card: Add project page, code link, and usage (#1)

Browse files

- Improve model card: Add project page, code link, and usage (f1d1483e5a5448e3ad42ee8eb72c2cee3dd1af42)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -13,6 +13,9 @@ This is a model from the paper [Thera: Aliasing-Free Arbitrary-Scale Super-Resol
13
  It enables SOTA arbitrary-scale super-resolution, leveraging a built-in analytically correct observation model
14
  for anti-aliasing when moving across scales.
15
 
 
 
 
16
  ## Model Details
17
 
18
  - **Description**: This model can be used to enable super-resolution of single images at arbitrary, non-integer scaling factors.
@@ -20,6 +23,12 @@ for anti-aliasing when moving across scales.
20
  - **Variant**: `Air`
21
  - **Training Dataset**: `DIV2K`
22
 
 
 
 
 
 
 
23
 
24
  ## License
25
 
 
13
  It enables SOTA arbitrary-scale super-resolution, leveraging a built-in analytically correct observation model
14
  for anti-aliasing when moving across scales.
15
 
16
+ Project page: https://therasr.github.io
17
+ Code: https://github.com/prs-eth/thera
18
+
19
  ## Model Details
20
 
21
  - **Description**: This model can be used to enable super-resolution of single images at arbitrary, non-integer scaling factors.
 
23
  - **Variant**: `Air`
24
  - **Training Dataset**: `DIV2K`
25
 
26
+ ## Sample Usage
27
+
28
+ Super-resolve any image with:
29
+ ```bash
30
+ > ./super_resolve.py IN_FILE OUT_FILE --scale 3.14 --checkpoint thera-rdn-pro.pkl
31
+ ```
32
 
33
  ## License
34