Raymondmax / EDVR

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks

We have merged EDVR into MMSR 😄

MMSR is an open source image and video super-resolution toolbox based on PyTorch. It is a part of the open-mmlab project developed by Multimedia Laboratory, CUHK. MMSR is based on our previous projects: BasicSR, ESRGAN, and EDVR.

---

EDVR [BasicSR] [DNI]

Paper | Project Page | Open VideoRestoration Doc (under construction)

Video Restoration with Enhanced Deformable Convolutional Networks

By Xintao Wang, Kelvin C.K. Chan, Ke Yu, Chao Dong, Chen Change Loy

EDVR won all four tracks in NTIRE 2019 Challenges on Video Restoration and Enhancement (CVPR19 Workshops).

Highlights

• A unified framework suitable for various video restoration tasks, e.g., super-resolution, deblurring, denoising, etc
• State of the art: Winners in NTIRE 2019 Challenges on Video Restoration and Enhancement
• Multi-GPU (distributed) training

Updates

[2019-06-28] Provide training logs and pretrained model for EDVR-M. Check here.
[2019-06-28] Support TOFlow testing (SR) (converted from officially released models).
[2019-06-12] Add training codes.
[2019-06-11] Add data preparation in wiki.
[2019-06-07] Support DUF testing (converted from officially released models).
[2019-05-28] Release testing codes.

Dependencies and Installation

• Python 3 (Recommend to use Anaconda)
• PyTorch >= 1.1
• NVIDIA GPU + CUDA
• Deformable Convolution. We use mmdetection's dcn implementation. Please first compile it.

  cd ./codes/models/archs/dcn
  python setup.py develop
  

• Python packages: pip install numpy opencv-python lmdb pyyaml
• TensorBoard:
  • PyTorch >= 1.1: pip install tb-nightly future

Dataset Preparation

We use datasets in LDMB format for faster IO speed. Please refer to wiki for more details.

Get Started

Please see wiki for the basic usage, i.e., training and testing.

Model Zoo and Baselines

Results and pre-trained models are available in the wiki-Model zoo.

Contributing

We appreciate all contributions. Please refer to mmdetection for contributing guideline.

Python code style
We adopt PEP8 as the preferred code style. We use flake8 as the linter and yapf as the formatter. Please upgrade to the latest yapf (>=0.27.0) and refer to the yapf configuration and flake8 configuration.

Before you create a PR, make sure that your code lints and is formatted by yapf.

Citation

@InProceedings{wang2019edvr,
  author    = {Wang, Xintao and Chan, Kelvin C.K. and Yu, Ke and Dong, Chao and Loy, Chen Change},
  title     = {EDVR: Video restoration with enhanced deformable convolutional networks},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  month     = {June},
  year      = {2019},
}
@Article{tian2018tdan,
  author    = {Tian, Yapeng and Zhang, Yulun and Fu, Yun and Xu, Chenliang},
  title     = {TDAN: Temporally deformable alignment network for video super-resolution},
  journal   = {arXiv preprint arXiv:1812.02898},
  year      = {2018},
}