Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou

Advanced Computer Vision LAB, National Cheng Kung University

Benchmark results on SRx4 without x2 pretraining. Mulit-Adds are calculated for a 64x64 input.

• ✅ 2024-03-31: Release the first version of the paper at Arxiv.
• ✅ 2024-04-14: DRCT is accepted by NTIRE 2024, CVPR.

@misc{hsu2024drct,
  title={DRCT: Saving Image Super-resolution away from Information Bottleneck}, 
  author={Chih-Chung Hsu and Chia-Ming Lee and Yi-Shiuan Chou},
  year={2024},
  eprint={2404.00722},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

• PyTorch >= 1.7 (Recommend NOT using torch 1.8!!! It would cause abnormal performance.)
• BasicSR == 1.3.4.9

Install Pytorch first. Then,

pip install -r requirements.txt
python setup.py develop

• Refer to ./options/test for the configuration file of the model to be tested, and prepare the testing data and pretrained model.
• Then run the following codes (taking DRCT_SRx4_ImageNet-pretrain.pth as an example):

python drct/test.py -opt options/test/DRCT_SRx4_ImageNet-pretrain.yml

The testing results will be saved in the ./results folder.

• Refer to ./options/test/DRCT_SRx4_ImageNet-LR.yml for inference without the ground truth image.

Note that the tile mode is also provided for limited GPU memory when testing. You can modify the specific settings of the tile mode in your custom testing option by referring to ./options/test/DRCT_tile_example.yml.

• Refer to ./options/train for the configuration file of the model to train.
• Preparation of training data can refer to this page. ImageNet dataset can be downloaded at the official website.
• The training command is like

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --master_port=4321 drct/train.py -opt options/train/train_DRCT_SRx2_from_scratch.yml --launcher pytorch

• Note that the default batch size per gpu is 4, which will cost about 20G memory for each GPU.

The training logs and weights will be saved in the ./experiments folder.

A part of our work has been facilitated by the HAT framework, and we are grateful for its outstanding contribution.

If you have any question, please email [email protected] to discuss with the author.