yanmenglu / EDVR Public

forked from xinntao/EDVR

Notifications You must be signed in to change notification settings
Fork 0
Star 0

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

xinntao.github.io/projects/edvr

Apache-2.0 license

0 stars 316 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 16 Commits
codes		codes
datasets		datasets
experiments/pretrained_models		experiments/pretrained_models
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md

Repository files navigation

EDVR

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).

Testing codes have been released.

Dependencies

Python 3 (Recommend to use Anaconda)
PyTorch = 1.0
NVIDIA GPU + CUDA
Deformable Convolution. We use Charles Shang's DCNv2 implementation. Please first compile it.
```
cd ./codes/models/modules/DCNv2
bash make.sh
```
Python packages: pip install numpy opencv-python lmdb

How to test

Download the pretrained models and testing datasts.
Run test_Vid4_REDS4_with_GT.py

About

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

xinntao.github.io/projects/EDVR

Apache-2.0 license

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 44.6%
Cuda 40.1%
C++ 11.0%
C 4.1%
Shell 0.2%