You can deploy this model and start earning money today!

lzxlog/
RealDAN

Views

No views yet

Original github repo is here

If this repo works for you, please cite our paper

bitex

@article{luo2023end,
  title={End-to-end Alternating Optimization for Real-World Blind Super Resolution},
  author={Luo, Zhengxiong and Huang, Yan and Li, Shang and Wang, Liang and Tan, Tieniu},
  journal={International Journal of Computer Vision (IJCV)},
  year={2023}
}

This repo is buid on the basis of BasicSR

Model Weights

Download the checkpoints of RealDAN.

Put the downloaded checkpoints into checkpoints

Inference

For inference on Real-World images

bash

cd codes/config/RealDAN
python3 inference.py \
--opt options/test/dan_edsr_gan_real.yml \
--input_dir=/dir/of/input/images \
--output_dir=/dir/of/saved/outputs

For inference on blurry images

bash

cd codes/config/KernelDAN
python3 inference.py \
--opt options/test/x4.yml \
--input_dir=/dir/of/input/images \
--output_dir=/dir/of/saved/outputs

Evaluation

For evaluation on DIV2K-Real, please download the dataset to your own path, and run

bash

cd codes/config/RealDAN
python3 test.py \
--opt options/test/dan_edsr_gan_syn.yml

and

bash

cd codes/config/RealDAN
python3 test.py \
--opt options/test/dan_edsr_syn.yml

For evaluation on DIV2KRK, please download the dataset to your own path, and run

bash

cd codes/config/KernelDAN
python3 test.py \
--opt options/test/x2.yml 

and

bash

cd codes/config/KernelDAN
python3 test.py \
--opt options/test/x4.yml 

lzxlog/RealDAN

Model Weights

Inference

Evaluation

lzxlog/
RealDAN