Skip to content

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

License

Notifications You must be signed in to change notification settings

researchmm/TTSR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TTSR (CVPR2020)

Official PyTorch implementation of the paper Learning Texture Transformer Network for Image Super-Resolution accepted in CVPR 2020.

Contents

Introduction

We proposed an approach named TTSR for RefSR task. Compared to SISR, RefSR has an extra high-resolution reference image whose textures can be utilized to help super-resolve low-resolution input.

Contribution

  1. We are one of the first to introduce the transformer architecture into image generation tasks. More specifically, we propose a texture transformer with four closely-related modules for image SR which achieves significant improvements over SOTA approaches.
  2. We propose a novel cross-scale feature integration module for image generation tasks which enables our approach to learn a more powerful feature representation by stacking multiple texture transformers.

Approach overview

Main results

Requirements and dependencies

  • python 3.7 (recommend to use Anaconda)
  • python packages: pip install opencv-python imageio
  • pytorch >= 1.1.0
  • torchvision >= 0.4.0

Model

Pre-trained models can be downloaded from onedrive, baidu cloud(0u6i), google drive.

  • TTSR-rec.pt: trained with only reconstruction loss
  • TTSR.pt: trained with all losses

Quick test

  1. Clone this github repo
git clone https://github.com/FuzhiYang/TTSR.git
cd TTSR
  1. Download pre-trained models and modify "model_path" in test.sh
  2. Run test
sh test.sh
  1. The results are in "save_dir" (default: ./test/demo/output)

Dataset prepare

  1. Download CUFED train set and CUFED test set
  2. Make dataset structure be:
  • CUFED
    • train
      • input
      • ref
    • test
      • CUFED5

Evaluation

  1. Prepare CUFED dataset and modify "dataset_dir" in eval.sh
  2. Download pre-trained models and modify "model_path" in eval.sh
  3. Run evaluation
sh eval.sh
  1. The results are in "save_dir" (default: ./eval/CUFED/TTSR)

Train

  1. Prepare CUFED dataset and modify "dataset_dir" in train.sh
  2. Run training
sh train.sh
  1. The training results are in "save_dir" (default: ./train/CUFED/TTSR)

Related projects

We also sincerely recommend some other excellent works related to us. ✨

Citation

@InProceedings{yang2020learning,
author = {Yang, Fuzhi and Yang, Huan and Fu, Jianlong and Lu, Hongtao and Guo, Baining},
title = {Learning Texture Transformer Network for Image Super-Resolution},
booktitle = {CVPR},
year = {2020},
month = {June}
}

Contact

If you meet any problems, please describe them in issues or contact:

About

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published