Recent studies have shown that a super-resolution generative adversarial network (SRGAN) can significantly improve the quality of single-image super-resolution. However, existing SRGAN methods also certain drawbacks, such as an insufficient feature utilization, large number parameters. To further enhance visual quality, we thoroughly studied three key components SRGAN, i.e., architecture, loss,...

Magnetotelluric (MT) surveying is an essential geophysical method for mapping subsurface electrical conductivity structures. The MT signal susceptible to cultural noise, and the intensity of noise growing with urbanization. Cultural increasingly difficult be removed by conventional data processing methods. We propose a novel time-series editing based on deep residual shrinkage network (DRSN) ad...