Home

Awesome

WACV23: ERVSR

Efficient Reference-based Video Super-Resolution (ERVSR)

Framework Overview

framework

Results

quality

Minimal test

You can simply check the PSNR and visualized results of exemplary data without any set-ups via minimal_test.ipynb.

Setting

  1. Clone this repository
git clone https://github.com/haewonc/ERVSR.git
  1. Match the dependencies following RefVSR.
  2. Download the RealMCVSR dataset.
  3. Download the pretrained SPyNet and place inside the directory net/.

Test

You can reproduce the results in our paper with commands below. The testing with default configuration file should work on a machine with GPU memory larger than 6GB.

  1. Download our pretrained ERVSR model and place inside the directory results/saved_models/.
  2. Run test.
python test.py --model results/saved_models/final.pth --data_offset $DATA_DIRECTORY$ --save_img True --save_dir results/test_imgs

Train

You can train ERVSR model with the command below. The training with default configuration file should work on a machine with NVIDIA RTX TITAN (Memory: 24GB).

python train.py -b $BATCH_SIZE$ -data_offset $DATA_DIRECTORY$