yangweipengscut / camixersr

CAMixerSR: Only Details Need More “Attention” (CVPR 2024)

CAMixerSR: Only Details Need More “Attention”

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).

---

Coming soon! We are focusing on ECCV and NTIRE, and planning to release implementations of CAMixerSR in a few months.

---

Citation

@article{wang2024camixersr,
  title={CAMixerSR: Only Details Need More "Attention"},
  author={Wang, Yan and Zhao, Shijie and Liu, Yi and Li, Junlin and Zhang, Li},
  journal={arXiv preprint arXiv:2402.19289},
  year={2024}
}