Among recent advances in SISR, attention mechanisms are crucial for high performance SR models. However, few works really discuss why attention works and how it works. In this work, we attempt to quantify and visualize the static attention mechanisms and show that not all attention modules are equally beneficial. We then propose attention in attention network (AN) for highly accurate image SR. This allows attention modules to specialize to beneficial examples without otherwise penalties and thus greatly improve the capacity of the attention network with little parameter overhead.
Attention in Attention Network for Image Super-Resolution
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
The Image Quality Assessment (IQA) methods are developed to measure the perceptual quality of images. However, while new algorithms have been continuously improving image restoration performance, we notice an increasing inconsistency between quantitative results and perceptual quality. In this paper, we contribute a new large-scale IQA dataset and build benchmarks for IQA methods.
Super Resolution Perception of Industrial Sensor Data
We propose a novel machine learning problem – the SRP problem as reconstructing high-quality data from unsatisfactory sensor data in industrial systems. A case study which performs SRP on smart meter data is then presented. A network, namely SRPNet, is proposed to generate high-frequency load data from low-frequency data. This technology makes it possible to empower existing industrial facilities without upgrading existing sensors or deploying additional sensors.