• Python 3 (Recommend to use Anaconda)

• NVIDIA GPU + CUDA

• Python packages:

  cd DMDC
  pip install -r requirements.txt

• Download training spectral images (Google Drive / Baidu Disk, code: mst1), training RGB images (Google Drive / Baidu Disk), validation spectral images (Google Drive / Baidu Disk), validation RGB images (Google Drive / Baidu Disk), and testing RGB images (Google Drive / Baidu Disk) from the competition website of NTIRE 2022 Spectral Reconstruction Challenge.

• Place the training spectral images and validation spectral images to /DMDC/dataset/Train_Spec/.

• Place the training RGB images and validation RGB images to /DMDC/dataset/Train_RGB/.

• Place the testing RGB images to /DMDC/dataset/Test_RGB/.

• Then this repo is collected as the following form:

  |--DMDC
      |--ARAD_1K 
      |--dataset 
          |--Train_Spec
              |--ARAD_1K_0001.mat
              |--ARAD_1K_0002.mat
              ： 
              |--ARAD_1K_0950.mat
    	  |--Train_RGB
              |--ARAD_1K_0001.jpg
              |--ARAD_1K_0002.jpg
              ： 
              |--ARAD_1K_0950.jpg
          |--Valid_Spec
              |--ARAD_1K_0901.mat
              |--ARAD_1K_0902.mat
              ： 
              |--ARAD_1K_0950.mat
    	  |--Valid_RGB
              |--ARAD_1K_0901.jpg
              |--ARAD_1K_0902.jpg
              ： 
              |--ARAD_1K_0950.jpg
          |--Test_RGB
              |--ARAD_1K_0951.jpg
              |--ARAD_1K_0952.jpg
              ： 
              |--ARAD_1K_1000.jpg
          |--split_txt
              |--train_list.txt
              |--valid_list.txt
          |--mask.mat

cd /DMDC/ARAD_1K/train_code/
python train.py --method DMDC_3stg  --batch_size 4  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_5stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_7stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_9stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0

(1) Download the pretrained model zoo from (will coming soon).

(2) Run the following command to test the model on the testing RGB images.

cd /DMDC/ARAD_1K/test_code/
python test.py --method DMDC_3stg  --batch_size 4  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_5stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_7stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_9stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0

• The repo is collected as the following form:

  |--DMDC
      |--simulation 
      |--datasets 
          |--cave_1024_28
            |--scene1.mat
            |--scene2.mat
            ：  
            |--scene205.mat
    	  |--cave_1024_28_RGB
            |--scene1.mat
            |--scene2.mat
            ：  
            |--scene205.mat
          |--cave_512_28
            |--scene1.mat
            |--scene2.mat
            ：  
            |--scene30.mat
          |--cave_512_28_RGB
            |--scene1.mat
            |--scene2.mat
            ：  
            |--scene30.mat
    	  |--TSA_simu_data
              |--Truth
                |--scene01.mat
                |--scene02.mat
                ： 
                |--scene10.mat
              |--Truth_RGB
                |--scene01.mat
                |--scene02.mat
                ： 
                |--scene10.mat
              |--mask.mat

1)Download cave_1024_28 (One Drive), CAVE_512_28 (Baidu Disk, code: ixoe | One Drive), KAIST_CVPR2021 (Baidu Disk, code: 5mmn | One Drive), TSA_simu_data (One Drive), TSA_real_data (One Drive), and then put them into the corresponding folders of datasets/ and recollect them as the following form: 2) Download cave_1024_28_RGB,Truth_RGB (Baidu Disk, code: y183))

##2.Prepare Pretrained ckpt:

Download pretrained (will comming soon) .

cd /DMDC/simulation/train_code/
python train.py --method DMDC_3stg  --batch_size 4  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_5stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_7stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python train.py --method DMDC_9stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0

cd /DMDC/simulation/test_code/
python test.py --method DMDC_3stg  --batch_size 4  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_5stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_7stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0
python test.py --method DMDC_9stg  --batch_size 2  --outf ./exp/DMDC_3stg/ --data_root ../dataset/  --gpu_id 0