Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,47 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf)
|
| 6 |
+
|
| 7 |
+
# 1xDeJPG_realplksr_otf
|
| 8 |
+
Scale: 1
|
| 9 |
+
Architecture: [RealPLKSR](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)
|
| 10 |
+
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)
|
| 11 |
+
|
| 12 |
+
Author: Philip Hofmann
|
| 13 |
+
License: CC-BY-0.4
|
| 14 |
+
Purpose: JPEG, Restoration
|
| 15 |
+
Subject: Photography
|
| 16 |
+
Input Type: Images
|
| 17 |
+
Release Date: 09.07.2024
|
| 18 |
+
|
| 19 |
+
Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)
|
| 20 |
+
Dataset Size: 6000
|
| 21 |
+
OTF (on the fly augmentations): Yes
|
| 22 |
+
Pretrained Model: This one used the 60 model as pretrain, while I used [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample) as a pretrain for the 60 model.
|
| 23 |
+
Iterations: 196'000
|
| 24 |
+
Batch Size: 24
|
| 25 |
+
GT Size: 64
|
| 26 |
+
|
| 27 |
+
Description:
|
| 28 |
+
A 1x dejpg model, trained with otf down to jpg 40 in both degradation processes, see the yml config file for details.
|
| 29 |
+
I also release the 1xDeJPG_realplksr_otf_60 model additionally, which had been trained with less jpg compression in comparison, down to 60 in both cases, where the hope was that it could give a bit higher quality on less compressed inputs.
|
| 30 |
+
The 40 model is released as default since it will be able to handle more compressed inputs in general.
|
| 31 |
+
Since these are trained with otf will slightly deblur. Examples here are compressed, and then recompressed, with jpg 40.
|
| 32 |
+
|
| 33 |
+
Showcase:
|
| 34 |
+
[Slowpics](https://slow.pics/c/c0Wft9H4)
|
| 35 |
+
[Imgsli](https://imgsli.com/Mjc3NzMw)
|
| 36 |
+
|
| 37 |
+
(Click on image for better view)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|