ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models

TL;DR

ReLayout is a novel method that improves content-aware layout generation by integrating relation reasoning and structured design concepts, resulting in more coherent, diverse, and aesthetically aligned layouts.

Contribution

It introduces explicit relation definitions and a prototype rebalance sampler to enhance the structural reasoning and style diversity in layout generation using large language models.

Findings

ReLayout outperforms existing methods in generating structured layouts.

The approach achieves layouts more aligned with human aesthetics.

It enhances explainability and diversity in layout generation.

Abstract

Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.