DeepHist：用于图像到图像转换的可区分联合和颜色直方图层
DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation
摘要：
我们介绍了DeepHist -一种新的深度学习框架，用于通过直方图层来增强网络，并通过解决图像到图像的翻译问题来展示其实力。具体来说，给定输入图像和参考颜色分布，我们的目标是生成具有输入（源）的结构外观（内容）但具有参考颜色的输出图像。其关键思想是一种新的技术，用于输出图像的联合直方图和颜色直方图的可区分构造。我们进一步定义了一个颜色分布损失的基础上的地球移动器的距离之间的输出和参考的颜色直方图和互信息损失的基础上的联合直方图的源和输出图像。在色彩转移、图像着色和$\rightarrow$照片边缘处理等任务中，控制了输出图像的色彩分布，取得了令人满意的结果。与Pix 2 Pix和CyclyGAN进行了比较。
英文摘要：
We present the DeepHist - a novel Deep Learning framework for augmenting a network by histogram layers and demonstrate its strength by addressing image-to-image translation problems. Specifically, given an input image and a reference color distribution we aim to generate an output image with the structural appearance (content) of the input (source) yet with the colors of the reference. The key idea is a new technique for a differentiable construction of joint and color histograms of the output images. We further define a color distribution loss based on the Earth Mover's Distance between the output's and the reference's color histograms and a Mutual Information loss based on the joint histograms of the source and the output images. Promising results are shown for the tasks of color transfer, image colorization and edges $\rightarrow$ photo, where the color distribution of the output image is controlled. Comparison to Pix2Pix and CyclyGANs are shown.
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。
