Structural Analogy from a Single Image Pair,Computer Graphics Forum

当前位置： X-MOL 学术 › Comput. Graph. Forum › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Structural Analogy from a Single Image Pair
Computer Graphics Forum ( IF 2.7 ) Pub Date : 2020-12-27 , DOI: 10.1111/cgf.14186
S. Benaim ₁ , R. Mokady ₁ , A. Bermano ₁ , L. Wolf _{1,

2}

Affiliation

The task of unsupervised image-to-image translation has seen substantial advancements in recent years through the use of deep neural networks. Typically, the proposed solutions learn the characterizing distribution of two large, unpaired collections of images, and are able to alter the appearance of a given image, while keeping its geometry intact. In this paper, we explore the capabilities of neural networks to understand image structure given only a single pair of images, A and B. We seek to generate images that are structurally aligned: that is, to generate an image that keeps the appearance and style of B, but has a structural arrangement that corresponds to A. The key idea is to map between image patches at different scales. This enables controlling the granularity at which analogies are produced, which determines the conceptual distinction between style and content. In addition to structural alignment, our method can be used to generate high quality imagery in other conditional generation tasks utilizing images A and B only: guided image synthesis, style and texture transfer, text translation as well as video translation. Our code and additional results are available in this https URL.

中文翻译：

来自单个图像对的结构类比

近年来，通过使用深度神经网络，无监督图像到图像转换的任务取得了重大进展。通常，所提出的解决方案学习两个大的、不成对的图像集合的特征分布，并且能够改变给定图像的外观，同时保持其几何结构完整。在本文中，我们探索了神经网络在仅给定一对图像 A 和 B 的情况下理解图像结构的能力。我们寻求生成结构对齐的图像：即生成保持外观和风格的图像的 B，但具有对应于 A 的结构排列。关键思想是在不同尺度的图像块之间进行映射。这可以控制产生类比的粒度，这决定了风格和内容之间的概念区别。除了结构对齐之外，我们的方法还可用于仅使用图像 A 和 B 在其他条件生成任务中生成高质量图像：引导图像合成、样式和纹理转移、文本翻译以及视频翻译。我们的代码和其他结果可在此 https URL 中找到。

更新日期：2020-12-27

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11