Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-4.0
|
3 |
+
pipeline_tag: image-to-image
|
4 |
+
tags:
|
5 |
+
- pytorch
|
6 |
+
- super-resolution
|
7 |
+
---
|
8 |
+
|
9 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xNomosWebPhoto_atd)
|
10 |
+
|
11 |
+
# 4xNomosWebPhoto_atd
|
12 |
+
|
13 |
+
Scale: 4
|
14 |
+
Architecture: [ATD](https://github.com/LabShuHangGU/Adaptive-Token-Dictionary)
|
15 |
+
Architecture Option: atd
|
16 |
+
|
17 |
+
|
18 |
+
Author: Philip Hofmann
|
19 |
+
License: CC-BY-0.4
|
20 |
+
Purpose: Restoration
|
21 |
+
Subject: Photography
|
22 |
+
Input Type: Images
|
23 |
+
Release Date: 07.06.2024
|
24 |
+
|
25 |
+
Dataset: Nomos-v2
|
26 |
+
Dataset Size: 6000
|
27 |
+
OTF (on the fly augmentations): No
|
28 |
+
Pretrained Model: 003_ATD_SRx4_finetune.pth
|
29 |
+
Iterations: 460'000
|
30 |
+
Batch Size: 6, 2
|
31 |
+
GT Size: 128, 192
|
32 |
+
|
33 |
+
Description:
|
34 |
+
|
35 |
+
4x ATD model for photography, trained with realistic noise, lens blur, jpg and webp re-compression.
|
36 |
+
ATD version of [4xNomosWebPhoto_RealPLKSR](https://github.com/Phhofm/models/releases/tag/4xNomosWebPhoto_RealPLKSR), trained on the same dataset and in the same way. For more information look into the [4xNomosWebPhoto_RealPLKSR](https://github.com/Phhofm/models/releases/tag/4xNomosWebPhoto_RealPLKSR) release, and the pdf file in its attachments.
|
37 |
+
|
38 |
+
Showcase:
|
39 |
+
[Slow Pics 18 Examples](https://slow.pics/s/GkS39XYi)
|
40 |
+
|
41 |
+

|
42 |
+

|
43 |
+

|
44 |
+

|
45 |
+

|
46 |
+

|
47 |
+

|
48 |
+

|
49 |
+

|
50 |
+

|
51 |
+

|
52 |
+

|