arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02416cs.CVcs.LG
收藏

用于版图生成的变分Transformer网络

Variational Transformer Networks for Layout Generation

Google Inc(谷歌公司);ETH Zürich(苏黎世联邦理工学院);Technische Universität München(慕尼黑工业大学)

Diego Martin Arroyo, Janis Postels, Federico Tombari

摘要:

生成模型能够合成不同类型的布局(例如文档、用户界面或家具布置),是辅助设计过程的有用工具,也是生成合成数据的第一步。我们利用自注意层的属性来捕获布局中元素之间的高级关系,并将其用作众所周知的变分自编码器(VAE)公式的构建块。我们提出的变分Transformer网络(VTN)是能够学习的利润,路线和其他全球性的设计规则,没有明确的监督。从我们的模型中采样的布局与训练数据具有高度的相似性,同时表现出吸引人的多样性。在对不同布局类型的公开基准的广泛评估中,VTN实现了最先进的多样性和感知质量。此外,我们展示了这种方法作为文档布局检测管道的一部分的功能。

英文摘要:

Generative models able to synthesize layouts of different kinds (e.g. documents, user interfaces or furniture arrangements) are a useful tool to aid design processes and as a first step in the generation of synthetic data, among other tasks. We exploit the properties of self-attention layers to capture high level relationships between elements in a layout, and use these as the building blocks of the well-known Variational Autoencoder (VAE) formulation. Our proposed Variational Transformer Network (VTN) is capable of learning margins, alignments and other global design rules without explicit supervision. Layouts sampled from our model have a high degree of resemblance to the training data, while demonstrating appealing diversity. In an extensive evaluation on publicly available benchmarks for different layout types VTNs achieve state-of-the-art diversity and perceptual quality. Additionally, we show the capabilities of this method as part of a document layout detection pipeline.

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。

↑