LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators
This addresses layout generation for graphic design and scene generation, offering a novel method but with incremental improvements over existing GAN approaches.
The paper tackles the problem of generating realistic graphic layouts by proposing LayoutGAN, a GAN that models geometric relations of 2D elements and uses a wireframe discriminator, achieving effective results in tasks like MNIST digit generation and document layout generation.
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 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 and tangram graphic design.