We aim at accelerating super-resolution (SR) networks on large images
(2K-8K). The large images are usually decomposed into small sub-images in
practical usages. Based on this processing, we found that different image
regions have different restoration difficulties and can be processed by
networks with different capacities. Intuitively, smooth areas are easier to
super-solve than complex textures. To utilize this property, we can adopt
appropriate SR networks to process different sub-images after the
decomposition. On this basis, we propose a new solution pipeline -- ClassSR
that combines classification and SR in a unified framework. In particular, it
first uses a Class-Module to classify the sub-images into different classes
according to restoration difficulties, then applies an SR-Module to perform SR
for different classes. The Class-Module is a conventional classification
network, while the SR-Module is a network container that consists of the
to-be-accelerated SR network and its simplified versions. We further introduce
a new classification method with two losses -- Class-Loss and Average-Loss to
produce the classification results. After joint training, a majority of
sub-images will pass through smaller networks, thus the computational cost can
be significantly reduced. Experiments show that our ClassSR can help most
existing methods (e.g., FSRCNN, CARN, SRResNet, RCAN) save up to 50% FLOPs on
DIV8K datasets. This general framework can also be applied in other low-level
vision tasks.

本文提出了一种新的基于 Classification 和 SR 模块的解决方案管道 (ClassSR)，可以在处理大型图像时加速超分辨率 (SR) 网络，通过分类不同的子图像并选择不同的 SR 网络对其进行处理，实现了分类和超分辨率的统一框架，并且通过两个损失方法，Class-Loss 和 Average-Loss，使得大多数子图像可以通过更小的网络，从而大大减少了计算成本，该方法在低级别视觉任务中也有应用前景。