用于高保真图像变换的谱一致UNet
Spectrally Consistent UNet for High Fidelity Image Transformations
摘要：
卷积神经网络（CNN）是目前用于许多成像任务的事实上的模型，因为它们具有很高的学习能力和架构质量。无处不在的UNet架构提供了一个有效的和多规模的解决方案，结合本地和全球信息。尽管UNet架构取得了成功，但使用上采样层可能会导致伪影。在这项工作中，提出了一种方法，用于评估的结构偏差的UNets和这些对输出的影响，在傅立叶域的影响的特点。提出了一种新的上采样模块，基于引导图像滤波器的新用途，其在UNet架构中使用时提供频谱一致的输出，形成引导UNet（GUNet）。GUNet架构的应用和评估，例如应用程序的逆色调映射/动态范围扩展和colourisation从灰度图像，并显示提供更高保真度的输出。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
