Need help with D3Dnet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

202 Stars 31 Forks 85 Commits 11 Opened issues


Repository for "Deformable 3D Convolution for Video Super-Resolution", SPL, 2020

Services available


Need anything else?

Contributors list

Deformable 3D Convolution for Video Super-Resolution

Pytorch implementation of deformable 3D convolution network (D3Dnet). [PDF]

Our code is based on cuda and can perform deformation in any dimension of 3D convolution.


Architecture of D3Dnet

Architecture of D3D


  • Python 3
  • pytorch (1.0.0), torchvision (0.2.2) / pytorch (1.2.0), torchvision (0.4.0)
  • numpy, PIL
  • Visual Studio 2015


Compile deformable 3D convolution:
1. Cd to

. 2. For Windows users, run
cmd make.bat
. For Linux users, run
. The scripts will build D3D automatically and create some folders. 3. See
for example usage.


Training dataset

  1. Download the Vimeo dataset and put the images in
  2. Cd to
    and run
    to generate training data as below:
    └── sequences
           ├── 00001
           ├── 00002
           ├── ...
    └── LR_x4
           ├── 00001
           ├── 00002
           ├── ...        
    ├── readme.txt 
    ├── sep_trainlist.txt
    ├── sep_testlist.txt
    └── generate_LR_Vimeo90K.m      

Test dataset

  1. Download the dataset Vid4 and SPMC-11 dataset in (Code: 4l5r) and put the folder in
  2. (optional) You can also download Vid4 and SPMC-11 or other video datasets and prepare test data in
    as below:
    └── dataset_1
         └── scene_1
               └── hr    
                  ├── hr_01.png  
                  ├── hr_02.png  
                  ├── ...
                  └── hr_M.png    
               └── lr_x4
                  ├── lr_01.png  
                  ├── lr_02.png  
                  ├── ...
                  └── lr_M.png   
         ├── ...        
         └── scene_M
    ├── ...    
    └── dataset_N      
    ## Results

Quantitative Results

Table 1. PSNR/SSIM achieved by different methods.

Table 2. Temporal consistency and computational efficiency achieved by different methods.

We have organized the Matlab code framework of Video Quality Assessment metric T-MOVIE and MOVIE. [Code]
Welcome to have a look and use our code.

Qualitative Results

Qualitative results achieved by different methods. Blue boxes represent the temporal profiles among different frames.

A demo video is available at


  author = {Ying, Xinyi and Wang, Longguang and Wang, Yingqian and Sheng, Weidong and An, Wei and Guo, Yulan},
  title = {Deformable 3D Convolution for Video Super-Resolution},
  journal = {IEEE Signal Processing Letters},
  volume = {27},
  pages = {1500-1504},
  year = {2020},


This code is built on [DCNv2] and [SOF-VSR]. We thank the authors for sharing their codes.


Please contact us at [email protected] for any question.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.