期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 43, 期 7, 页码 2388-2399出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2963663
关键词
Layout; Generators; Rendering (computer graphics); Visualization; Three-dimensional displays; Optimization; Generative adversarial networks; graphic design; layout; wireframe
LayoutGAN synthesizes layouts by modeling geometric relations of 2D elements, uses self-attention modules and differentiable wireframe rendering layer to optimize layouts, and validates its effectiveness in various experiments.
Layout is important for graphic design and scene generation. We propose a novel Generative Adversarial Network, called LayoutGAN, that synthesizes layouts by modeling geometric relations of different types of 2D elements. The generator of LayoutGAN takes as input a set of randomly-placed 2D graphic elements, represented by vectors and uses self-attention modules to refine their labels and geometric parameters jointly to produce a realistic layout. Accurate alignment is critical for good layouts. We, thus, propose a novel differentiable wireframe rendering layer that maps the generated layout to a wireframe image, upon which a CNN-based discriminator is used to optimize the layouts in image space. We validate the effectiveness of LayoutGAN in various experiments including MNIST digit generation, document layout generation, clipart abstract scene generation, tangram graphic design, mobile app layout design, and webpage layout optimization from hand-drawn sketches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据