Convolutional Neural Networks (CNNs) are the current de-facto models used for many imaging tasks due to their high learning capacity as well as their architectural qualities. The ubiquitous UNet architecture provides an efficient and multi-scale solution that combines local and global information. Despite the success of UNet architectures, the use of upsampling layers can cause artefacts. In this work, a method for assessing the structural biases of UNets and the effects these have on the outputs is presented, characterising their impact in the Fourier domain. A new upsampling module is proposed, based on a novel use of the Guided Image Filter, that provides spectrally consistent outputs when used in a UNet architecture, forming the Guided UNet (GUNet). The GUNet architecture is applied and evaluated for example applications of inverse tone mapping/dynamic range expansion and colourisation from grey-scale images and is shown to provide higher fidelity outputs.
@article{arxiv.2004.10696,
title = {Spectrally Consistent UNet for High Fidelity Image Transformations},
author = {Demetris Marnerides and Thomas Bashford-Rogers and Kurt Debattista},
journal= {arXiv preprint arXiv:2004.10696},
year = {2020}
}