To satisfy the rapidly increasing demands on the large image (2K-8K)
super-resolution (SR), prevailing methods follow two independent tracks: 1)
accelerate existing networks by content-aware routing, and 2) design better
super-resolution networks via token mixer refining. Despite directness, they
encounter unavoidable defects (e.g., inflexible route or non-discriminative
processing) limiting further improvements of quality-complexity trade-off. To
erase the drawbacks, we integrate these schemes by proposing a content-aware
mixer (CAMixer), which assigns convolution for simple contexts and additional
deformable window-attention for sparse textures. Specifically, the CAMixer uses
a learnable predictor to generate multiple bootstraps, including offsets for
windows warping, a mask for classifying windows, and convolutional attentions
for endowing convolution with the dynamic property, which modulates attention
to include more useful textures self-adaptively and improves the representation
capability of convolution. We further introduce a global classification loss to
improve the accuracy of predictors. By simply stacking CAMixers, we obtain
CAMixerSR which achieves superior performance on large-image SR, lightweight
SR, and omnidirectional-image SR.

为了满足对大尺寸图像（2K-8K）超分辨率（SR）的迅速增长需求，本研究提出了一种内容感知混合器（CAMixer），通过使用卷积处理简单的上下文和可变形窗口注意力处理稀疏纹理，使卷积具有动态属性，自适应地调节注意力并改善表示能力，通过简单堆叠 CAMixer，得到了在大图像 SR、轻量级 SR 和全方位图像 SR 上取得优秀性能的 CAMixerSR。