Home

Awesome

PPON

Pytorch implemention of "Progressive Perception-Oriented Network for Single Image Super-Resolution"

[arXiv] [Information Sciences]

<table> <tr> <td> <img src="figures/Structure.png" width="480"> <br /> <em> The schematics of the Progressive Perception-Oriented Network</em> </td> <td> <img height="400" src="figures/269.gif"> </td> </tr> </table> <p align="center"> <img src="figures/show.jpg" width="960"> <br /> <em> The example results</em> </p> <p align="center"> <img src="figures/visualization2.png" width="960"> <br /> <em> Visualization of intermediate feature maps</em> </p> <p align="center"> <img src="figures/structure_inference.png" width="480"> <br /> <em> The inference architecture of our PPON.</em> </p> <table> <tr> <td><img src="figures/278.gif"></td> <td><img src="figures/300.gif"></td> </tr> </table>

Testing

Pytorch 1.1

python test_PPON.py --test_hr_folder Test_Datasets/PIRM_Val/ --test_lr_folder Test_Datasets/PIRM_Val_LR/

Training

python scripts/png2npy.py --pathFrom /path/to/DF2K/ --pathTo /path/to/DF2K_decoded/
python train.py --nEpochs 1000 --test_every 690 --which_model "content" --lr_steps [200, 400, 600, 800] --save_path 'ckpt_stage1'

(stage 2, structure)

python train.py --nEpochs 300 --test_every 138 --which_model "structure" --pixel_weight 0 --structure_weight 1 --lr_steps [100, 150, 200, 250] --save_path 'ckpt_stage2'

(stage3, perceptual)

python train.py --nEpochs 300 --test_every 138 --which_model "perceptual" --pixel_weight 0 --feature_weight 1 --gan_weight 0.005 --lr_steps [100, 150, 200, 250] --save_path 'ckpt_stage3'

PI VS LPIPS

PI-VS-LPIPS As illustrated in the above picture, we can obviously see that the PI score of EPSR3 (2.2666) is even better than HR (2.3885), but EPSR3 shows unnatural and lacks proper texture and structure.

Example Results

Perceptual-results-1 Perceptual-results-2

Citation

If you find PPON useful in your research, please consider citing:

@article{Hui-PPON-2019,
  title={Progressive Perception-Oriented Network for Single Image Super-Resolution},
  author={Hui, Zheng and Li, Jie and Gao, Xinbo and Wang, Xiumei},
  journal={arXiv:1907.10399v1},
  year={2019}
}

@article{Hui-PPON-2021,
  title={Progressive Perception-Oriented Network for Single Image Super-Resolution},
  author={Hui, Zheng and Li, Jie and Gao, Xinbo and Wang, Xiumei},
  journal={Information Sciences},
  volume = {546},
  pages = {769-786},
  year={2021}
}