SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior

2025-10-17

AI Summary

This work addresses background-image-driven, content-aware layout generation—a challenging task where existing methods suffer from high failure rates in complex scenarios due to the absence of feedback-driven self-correction mechanisms. To tackle this, we propose the Stepwise Evolutionary Generation Architecture (SEGA), a two-stage inference framework comprising coarse layout initialization followed by fine-grained optimization. SEGA is the first to integrate human-like stepwise evolutionary reasoning with design priors—including alignment, contrast, and white space—directly into the generative process. We further introduce GenPoster-100K, a large-scale, diverse poster dataset, to support training and comprehensive evaluation. Extensive experiments demonstrate that SEGA achieves state-of-the-art performance across multiple benchmarks, significantly improving visual harmony, content coherence, and aesthetic plausibility of generated layouts. These results validate the effectiveness and generalizability of our feedback-driven, prior-guided co-design paradigm.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Models for Web evolution
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In this paper, we study the content-aware layout generation problem, which aims to automatically generate layouts that are harmonious with a given background image. Existing methods usually deal with this task with a single-step reasoning framework. The lack of a feedback-based self-correction mechanism leads to their failure rates significantly increasing when faced with complex element layout planning. To address this challenge, we introduce SEGA, a novel Stepwise Evolution Paradigm for Content-Aware Layout Generation. Inspired by the systematic mode of human thinking, SEGA employs a hierarchical reasoning framework with a coarse-to-fine strategy: first, a coarse-level module roughly estimates the layout planning results; then, another refining module performs fine-level reasoning regarding the coarse planning results. Furthermore, we incorporate layout design principles as prior knowledge into the model to enhance its layout planning ability. Besides, we present GenPoster-100K that is a new large-scale poster dataset with rich meta-information annotation. The experiments demonstrate the effectiveness of our approach by achieving the state-of-the-art results on multiple benchmark datasets. Our project page is at: https://brucew91.github.io/SEGA.github.io/

Problem

• Generating layouts harmonious with background images
• Addressing failure rates in complex element layout planning
• Incorporating design principles as prior knowledge

Innovation

• Stepwise evolution paradigm for layout generation
• Hierarchical coarse-to-fine reasoning framework
• Incorporates layout design principles as prior knowledge