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

2026-04-08

AI Summary

This study addresses the domain shift between image and layout paired data in advertising poster generation, which often leads to misalignment between generated layouts and product image content. To tackle this issue, the authors introduce the CGL dataset and propose two image-aware layout generation methods: CGL-GAN, which employs Gaussian blur to inpaint missing regions, and PDA-GAN, which pioneers a pixel-level discriminator for unsupervised domain adaptation, effectively bridging the domain gap between inpainted posters and clean product images. The work innovatively integrates shallow feature connections with a pixel-level discrimination mechanism and introduces three content-aware evaluation metrics to quantitatively assess semantic consistency between layouts and images. Experimental results demonstrate that PDA-GAN achieves state-of-the-art performance in both quantitative and qualitative evaluations, generating high-quality ad layouts that closely match the visual textures of input images.

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.

Problem

• image-aware layout generation
• domain adaptation
• advertising poster design
• domain gap
• graphic layout

Innovation

• GAN-based domain adaptation
• image-aware layout generation
• pixel-level discriminator
• content-aware metrics
• graphic design