Repository for "Deformable 3D Convolution for Video Super-Resolution", SPL, 2020
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.
Compile deformable 3D convolution:
1. Cd to
code/dcn. 2. For Windows users, run
cmd make.bat. For Linux users, run
bash make.sh. The scripts will build D3D automatically and create some folders. 3. See
test.pyfor example usage.
code/data/Vimeo.
code/data/Vimeoand run
generate_LR_Vimeo90K.mto generate training data as below:
Vimeo └── sequences ├── 00001 ├── 00002 ├── ... └── LR_x4 ├── 00001 ├── 00002 ├── ... ├── readme.txt ├── sep_trainlist.txt ├── sep_testlist.txt └── generate_LR_Vimeo90K.m
code/data.
code/dataas below:
data └── 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
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 achieved by different methods. Blue boxes represent the temporal profiles among different frames.
A demo video is available at https://wyqdatabase.s3-us-west-1.amazonaws.com/D3Dnet.mp4
@article{D3Dnet, 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.