Official Repo of TCNet

We thank Xintao and his group for their open-sourced image/video processing ToolBox BasicSR. Our codes are totally based on it.

Prerequisites

• Linux Ubuntu 18.04+
• Anaconda
• Python 3.7+
• Pytorch 1.7+

DatasetsPreparation

• REDS

  1. Download the datasets from the official website.
  2. Regroup the training and validation datasets (following EDVR).
  3. Make LMDB files when necessary. Please refer to LMDB Description.

• Vimeo90K

  1. Download the dataset: Septuplets dataset All GroundTruth images (82GB).
  2. Generate the low-resolution images. Refer to the scripts files for BI & BD degradation.
  3. Make LMDB files when necessary. Please refer to LMDB Description.

GetStarted

• Following BasicSR illustration for installation.
• Fetching network source files and other util files to BasicSR's arch folder.
• Following BasicSR illustration for training and testing.

Citation

@article{TCNet,
  title = {Temporal Consistency Learning of Inter-Frames for Video Super-Resolution},
  author = {Liu, Meiqin and Jin, Shuo and Yao, Chao and Lin, Chunyu and Zhao, Yao},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2022},
  publisher = {IEEE}
}