- ✅ 2023-09-09: Release the codes and results of HMA.
- ✅ 2024-09-26: Release the pre-train models of HMA.
Benchmark results on SRx4.
| Model | Set5 | Set14 | BSD100 | Urban100 | Manga109 |
|---|---|---|---|---|---|
| SwinIR | 32.92 | 29.09 | 27.92 | 27.45 | 32.03 |
| HMA | 33.38 | 29.51 | 28.13 | 28.69 | 33.19 |
Comparison with the state-of-the-art methods.
Install Pytorch first. Then,
pip install -r requirements.txt
python setup.py develop
- Refer to
./options/testfor the configuration file of the model to be tested, and prepare the testing data and pretrained model. - The pretrained models are available at Google Drive.
- Then run the following codes (taking
HMA_SRx2_pretrain.pthas an example):
python hma/test.py -opt options/test/HMA_SRx2.yml
The testing results will be saved in the ./results folder.
- Refer to
./options/trainfor 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 --use_env --master_port=4321 hma/train.py -opt options/train/train_HMA_SRx4_from_Imagenet.yml --launcher pytorch
The training logs and weights will be saved in the ./experiments folder.
The inference results on benchmark datasets are available at Google Drive.
@InProceedings{Chu_2024_CVPR,
author = {Chu, Shu-Chuan and Dou, Zhi-Chao and Pan, Jeng-Shyang and Weng, Shaowei and Li, Junbao},
title = {HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2024},
pages = {6257-6266}
}
If you have any question, please email [email protected] to discuss with the authors.