AllenZYJ/EDVR

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

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

1. Download the pretrained models and testing datasts.

2. Run test_Vid4_REDS4_with_GT.py

Test lines.