Overview: We propose CAMixerSR, a new approach integrating content-aware accelerating framework and token mixer design, to pursue more efficient SR inference via assigning convolution for simple regions but window-attention for complex textures. It exhibits excellent generality and attains competitive results among state-of-the-art models with better complexity-performance trade-offs on large-image SR, lightweight SR, and omnidirectional-image SR.
This repository contains PyTorch implementation for CAMixerSR (CVPR 2024).
The main codes and pre-trained models have been uploaded. We are planning to replenish the README of CAMixerSR in a few weeks.
pip install -r requirements.txt
Training: DIV2K.
Testing: F2K, Test2K, Test4K, Test8K (Google Drive/Baidu Netdisk).
Testing: Set5, Set14, BSD100, Urban100, Manga109 (Google Drive/Baidu Netdisk).
Training: lau dataset.
Clone this repository and change the directory to ./codes
git clone https://github.com/icandle/CAMixerSR.git
cd codes
Testing: Change the dataset path of example option to your datasets and test with the command:
python basicsr/test.py -opt ../options/test/test_x4.yml
We would thank BasicSR, ClassSR, and OSRT for their enlightening work!
@article{wang2024camixersr,
title={CAMixerSR: Only Details Need More ``Attention"},
author={Wang, Yan and Liu, Yi and Zhao, Shijie and Li, Junlin and Zhang, Li},
journal={arXiv preprint arXiv:2402.19289},
year={2024}
}