This repository is an official implementation of the paper "Adaptive Pixel Classification and Equivalent Large Kernels for Lightweight Image Super-Resolution" for ICME2025.
Download the pretrained models for tesing or training.
Training and benchmark datasets can be downloaded from DIV2K and benchmarks, respectively.
git clone https://github.com/What-you-ever/PCLKN.git
conda create -n PCLKN python=3.9
conda activate PCLKN
pip install -r requirements.txt# x2
python basicsr/test.py -opt options/test/PCLKNSR_x2.yml
# x3
python basicsr/test.py -opt options/test/PCLKNSR_x2.yml
# x4
python basicsr/test.py -opt options/test/PCLKNSR_x4.yml# x2
python basicsr/test.py -opt options/test/PCLKNSR_x2.yml
# x3
python basicsr/test.py -opt options/test/PCLKNSR_x2.yml
# x4
python basicsr/test.py -opt options/test/PCLKNSR_x4.ymlThis project is built on BasicSR and ATD. Special thanks to their excellent works!