CVMar 14, 2024

Desigen: A Pipeline for Controllable Design Template Generation

arXiv:2403.09093v124 citationsCVPR
Originality Incremental advance
AI Analysis

This addresses the effort-intensive task of manual template creation for designers, though it appears incremental as it builds on existing diffusion and Transformer models.

The paper tackles the problem of automatically generating design templates (e.g., banners, slides) by proposing Desigen, a pipeline that creates background images and harmonious layouts, with experiments on over 40k advertisement banners showing it generates high-quality templates comparable to human designers.

Templates serve as a good starting point to implement a design (e.g., banner, slide) but it takes great effort from designers to manually create. In this paper, we present Desigen, an automatic template creation pipeline which generates background images as well as harmonious layout elements over the background. Different from natural images, a background image should preserve enough non-salient space for the overlaying layout elements. To equip existing advanced diffusion-based models with stronger spatial control, we propose two simple but effective techniques to constrain the saliency distribution and reduce the attention weight in desired regions during the background generation process. Then conditioned on the background, we synthesize the layout with a Transformer-based autoregressive generator. To achieve a more harmonious composition, we propose an iterative inference strategy to adjust the synthesized background and layout in multiple rounds. We constructed a design dataset with more than 40k advertisement banners to verify our approach. Extensive experiments demonstrate that the proposed pipeline generates high-quality templates comparable to human designers. More than a single-page design, we further show an application of presentation generation that outputs a set of theme-consistent slides. The data and code are available at https://whaohan.github.io/desigen.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes