From b18f8f24b1d0710aa7c39f62f6239c057601ae3a Mon Sep 17 00:00:00 2001
From: Syed Waqas Zamir <41057533+swz30@users.noreply.github.com>
Date: Sat, 28 Mar 2020 18:09:48 +0400
Subject: [PATCH] scripts to perform denoising in RAW and sRGB domains

---
 README.md | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/README.md b/README.md
index 02a0b65..a4d9d86 100644
--- a/README.md
+++ b/README.md
@@ -42,6 +42,35 @@ Given a synthetic RAW noisy image as input, the RAW2RGB network branch maps it t
   <br/>
 </p>
 
+## Evaluation
+#### Denoising RAW images of DND
+- Download the [model](https://drive.google.com/file/d/1yjI3JtfC1IluGB0LRlnpPTAY_UyY9mG8/view?usp=sharing) and place it in ./pretrained_models/denoising/
+- Download RAW [images](https://drive.google.com/drive/folders/15Bay1UJURlbP7kpS10_fJ96MxQ6B03Xv?usp=sharing) of DND and place them in ./datasets/dnd/dnd_raw/
+- Run
+```
+   $ python test_dnd_raw.py --save_images
+```
+#### Denoising RAW images of SIDD
+- Download the [model](https://drive.google.com/file/d/1m2A4goZENg_kKV1-FJoeg1rBqLj6WRIm/view?usp=sharing) and place it in ./pretrained_models/denoising/
+- Download RAW [images](https://drive.google.com/drive/folders/1invur2uE-QXHh-btHTZQetFcgjUAfbwc?usp=sharing) of SIDD and place them in ./datasets/sidd/sidd_raw/
+- Run
+```
+   $ python test_sidd_raw.py --save_images
+```
+#### Denoising sRGB images of DND
+- Download the [model](https://drive.google.com/file/d/1740sYH7bG-c-jL5wc3e1_NOpxwGTXS9c/view?usp=sharing) and place it in ./pretrained_models/denoising/
+- Download sRGB [images](https://drive.google.com/drive/folders/101AfVtkfizl20-XQ3leNt2cE_rI5ypeu?usp=sharing) of DND and place them in ./datasets/dnd/dnd_rgb/noisy/
+- Run
+```
+   $ python test_dnd_rgb.py --save_images
+```
+#### Denoising sRGB images of SIDD
+- Download the [model](https://drive.google.com/file/d/1sraG9JKmp0ieLjntRL7Jj2FXBrPr-YVp/view?usp=sharing) and place it in ./pretrained_models/denoising/
+- Download sRGB [images](https://drive.google.com/drive/folders/1JGoCXqHESBIocpDabk74mnee6RA3oCoP?usp=sharing) of SIDD and place them in ./datasets/sidd/sidd_rgb/
+- Run
+```
+   $ python test_sidd_rgb.py --save_images
+```
 ## Results on Real Image Datasets
 Experiments are performed for denoising images in RAW and sRGB spaces.