ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

by   Xiangtao Kong, et al.

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 DIV8K datasets. This general framework can also be applied in other low-level vision tasks.


page 4

page 6

page 15

page 16


Learning for Scale-Arbitrary Super-Resolution from Scale-Specific Networks

Recently, the performance of single image super-resolution (SR) has been...

RAM: Residual Attention Module for Single Image Super-Resolution

Attention mechanisms are a design trend of deep neural networks that sta...

SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image

The rapid identification and accurate diagnosis of breast cancer, known ...

Component Divide-and-Conquer for Real-World Image Super-Resolution

In this paper, we present a large-scale Diverse Real-world image Super-R...

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

Normalizing flows have recently demonstrated promising results for low-l...

Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

Rendering high-resolution (HR) graphics brings substantial computational...

Please sign up or login with your details

Forgot password? Click here to reset