分步演化框架提升复杂版面生成质量
SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior
- 分步演化：粗粒度规划后精细修正，模拟人类思考过程
- 在多个数据集上达最优，复杂布局失败率显著降低
- 融合设计原则先验，适合需要高质量视觉排版的场景
本文研究内容感知版面生成问题，旨在自动生成与给定背景图像协调的版面。现有方法多采用单步推理框架，缺乏反馈式自我修正机制，在处理复杂元素布局时失败率明显上升。为此，我们提出SEGA——一种新型的分步演化范式。受人类系统化思维启发，SEGA采用从粗到精的分层推理框架：先由粗粒度模块大致估计布局结果，再由精修模块基于此进行细粒度推理。此外，我们将版面设计原则作为先验知识融入模型，增强其布局规划能力。同时，我们构建了新的大规模海报数据集GenPoster-100K，包含丰富的元信息标注。实验表明，该方法在多个基准数据集上达到当前最优性能。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。