VASCAR：通过视觉感知自校正的内容感知布局生成
VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
AI总结：
本文提出无需训练的VASCAR方法，通过让大型视觉语言模型参照渲染布局图像进行视觉感知自校正，解决了LLMs无法感知图像导致的内容感知布局生成局限，并在GPT-4o和Gemini上取得SOTA效果。
摘要：
大型语言模型（LLMs）因其能够生成结构化描述语言（如HTML或JSON）而在布局生成中已被证明有效。本文认为，尽管LLMs在某些情况下表现尚可，但其无法感知图像的内在局限限制了它们在需要视觉内容的任务中的有效性，例如内容感知布局生成。因此，我们探索大型视觉语言模型（LVLMs）是否可以应用于内容感知布局生成。为此，受设计师迭代修改和启发式评估工作流程的启发，我们提出了无需训练的视觉感知自校正布局生成方法VASCAR。VASCAR使LVLMs（如GPT-4o和Gemini）能够参照渲染后的布局图像迭代地优化其输出，这些图像以彩色边界框的形式可视化在海报背景（即画布）上。大量实验和用户研究表明VASCAR的有效性，实现了最先进（SOTA）的布局生成质量。此外，VASCAR在GPT-4o和Gemini上的泛化能力证明了其通用性。
英文摘要：
Large language models (LLMs) have proven effective for layout generation due to their ability to produce structure-description languages, such as HTML or JSON. In this paper, we argue that while LLMs can perform reasonably well in certain cases, their intrinsic limitation of not being able to perceive images restricts their effectiveness in tasks requiring visual content, e.g., content-aware layout generation. Therefore, we explore whether large vision-language models (LVLMs) can be applied to content-aware layout generation. To this end, inspired by the iterative revision and heuristic evaluation workflow of designers, we propose the training-free Visual-Aware Self-Correction LAyout GeneRation (VASCAR). VASCAR enables LVLMs (e.g., GPT-4o and Gemini) iteratively refine their outputs with reference to rendered layout images, which are visualized as colored bounding boxes on poster background (i.e., canvas). Extensive experiments and user study demonstrate VASCAR's effectiveness, achieving state-of-the-art (SOTA) layout generation quality. Furthermore, the generalizability of VASCAR across GPT-4o and Gemini demonstrates its versatility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
