RealBasicVSR

[Paper]

This is the official repository of “Investigating Tradeoffs in Real-World Video Super-Resolution, arXiv”. This repository contains codes, colab, video demos of our work.

Authors: Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy, Nanyang Technological University

Acknowedgement: Our work is built upon MMEditing. The code will also appear in MMEditing soon. Please follow and star this repository and MMEditing!

News

  • 29 Nov 2021: Test code released
  • 25 Nov 2021: Initialize with video demos

Table of Content

  1. Video Demos
  2. Code
  3. VideoLQ Dataset
  4. Citations

Video Demos

The videos have been compressed. Therefore, the results are inferior to that of the actual outputs.

output.mp4


output.mp4


output.mp4


output.mp4


Code

Installation

  1. Install PyTorch and torchvision following the official instructions, e.g.,

conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=10.1 -c pytorch
  1. Install mim and mmcv-full

pip install openmim
mim install mmcv-full
  1. Install mmedit

pip install mmedit

Inference

  1. Download the pre-trained weights to checkpoints/. (Dropbox / Google Drive)

  2. Run the following command:

python inference_realbasicvsr.py ${CONFIG_FILE} ${CHECKPOINT_FILE} ${INPUT_DIR} ${OUTPUT_DIR} --max-seq-len=${MAX_SEQ_LEN} --is_save_as_png=${IS_SAVE_AS_PNG}  --fps=${FPS}

This script supports both images and videos as inputs and outputs. You can simply change ${INPUT_DIR} and ${OUTPUT_DIR} to the paths corresponding to the video files, if you want to use videos as inputs and outputs. But note that saving to videos may induce additional compression, which reduces output quality.

For example:

  1. Images as inputs and outputs

python inference_realbasicvsr.py configs/realbasicvsr_x4.py checkpoints/RealBasicVSR_x4.pth data/demo_000 results/demo_000
  1. Video as input and output

python inference_realbasicvsr.py configs/realbasicvsr_x4.py checkpoints/RealBasicVSR_x4.pth data/demo_001.mp4 results/demo_001.mp4 --fps=12.5

Training

To be appeared.

VideoLQ Dataset

You can download the dataset using Dropbox or Google Drive.

Citations

@article{chan2021investigating,
  author = {Chan, Kelvin C.K. and Zhou, Shangchen and Xu, Xiangyu and Loy, Chen Change},
  title = {Investigating Tradeoffs in Real-World Video Super-Resolution},
  journal = {arXiv preprint arXiv:2111.12704},
  year = {2021}
}

GitHub

View Github