Casper Kaae Sønderby, Jose Caballero, Lucas Theis, Wenzhe Shi, Ferenc Huszár
TL;DR该研究探讨使用最大后验估计推理方法来解决图像超分辨率问题,并介绍了基于神经网络的自动编码器估计的解决方案,其中使用了 3 种方法以优化 GAN 的效果。
Abstract
image super-resolution (SR) is an underdetermined inverse problem, where a
large number of plausible high-resolution images can explain the same
downsampled image. Most current single image SR methods use empirical risk
minimisation, often with a pixel-wise mean squared error (MSE) los