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.
Model | Params | Multi-Adds | Forward | FLOPs | Set5 | Set14 | BSD100 | Urban100 | Manga109 |
---|---|---|---|---|---|---|---|---|---|
HAT | 9.62M | 11.22G | 2053M | 42.18G | 33.04 | 29.23 | 28.00 | 27.97 | 32.48 |
DRCT | 10.44M | 5.92G | 1857M | 7.92G | 33.11 | 29.35 | 28.18 | 28.06 | 32.59 |
HAT-L | 40.84M | 76.69G | 5165M | 79.60G | 33.30 | 29.47 | 28.09 | 28.60 | 33.09 |
DRCT-L | 27.58M | 9.20G | 4278M | 11.07G | 33.37 | 29.54 | 28.16 | 28.70 | 33.14 |
-
โ 2024-03-31: Release the first version of the paper at Arxiv.
-
โ 2024-04-14: DRCT is accepted by NTIRE 2024, CVPR.
-
The pretrained model will be released.
-
MambaDRCT will be released.
-
Real_DRCT_GAN will be released.
- PyTorch >= 1.7 (Recommend NOT using torch 1.8!!! It would cause abnormal performance.)
- BasicSR == 1.3.4.9
git clone https://github.com/ming053l/DRCT.git
conda create --name drct python=3.8 -y
conda activate drct
# CUDA 11.6
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6 -c pytorch -c conda-forge
cd DRCT
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.
- Validation data can be download at this page.
- 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
The training logs and weights will be saved in the ./experiments
folder.
@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}
}
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.