GAN-based Domain Adaptation for Image-aware Layout Generation in Advertising Poster Design

TL;DR

This paper introduces a GAN-based approach with domain adaptation to generate image-aware advertising poster layouts, utilizing a new paired dataset and novel metrics for evaluation.

Contribution

It presents two GAN models, including PDA-GAN with pixel-level discrimination, and a new dataset for training and evaluating image-aware layout generation.

Findings

PDA-GAN outperforms existing models in quantitative metrics.

The proposed metrics effectively evaluate the relationship between graphic elements and image content.

The models generate high-quality, visually coherent poster layouts.

Abstract

Layout plays a crucial role in graphic design and poster generation. Recently, the application of deep learning models for layout generation has gained significant attention. This paper focuses on using a GAN-based model conditioned on images to generate advertising poster graphic layouts, requiring a dataset of paired product images and layouts. To address this task, we introduce the Content-aware Graphic Layout Dataset (CGL-Dataset), consisting of 60,548 paired inpainted posters with annotations and 121,000 clean product images. The inpainting artifacts introduce a domain gap between the inpainted posters and clean images. To bridge this gap, we design two GAN-based models. The first model, CGL-GAN, uses Gaussian blur on the inpainted regions to generate layouts. The second model combines unsupervised domain adaptation by introducing a GAN with a pixel-level discriminator (PD), abbreviated as PDA-GAN, to generate image-aware layouts based on the visual texture of input images. The PD is connected to shallow-level feature maps and computes the GAN loss for each input-image pixel. Additionally, we propose three novel content-aware metrics to assess the model's ability to capture the intricate relationships between graphic elements and image content. Quantitative and qualitative evaluations demonstrate that PDA-GAN achieves state-of-the-art performance and generates high-quality image-aware layouts.