多智能体协同驱动的迭代式视觉叙事合成
Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis
AI总结：
本文提出RCPS框架，通过深度叙事规划、自适应布局和迭代优化提升演示生成质量，并设计PREVAL评估框架，实验证明其显著优于基线且接近人类专家水平。
摘要：
高质量媒体演示的自动生成具有挑战性，需要稳健的内容提取、叙事规划、视觉设计以及整体质量优化。现有方法生成的演示往往存在逻辑不一致和布局欠佳的问题，难以达到专业标准。为应对这些挑战，我们提出了RCPS（Reflective Coherent Presentation Synthesis，反思式连贯演示合成），这是一个集成三个关键组件的新框架：（1）深度结构化叙事规划；（2）自适应布局生成；（3）迭代优化循环。此外，我们提出了PREVAL，一个基于偏好的评估框架，采用理由增强的多维模型，从内容、连贯性和设计三个维度评估演示质量。实验结果表明，RCPS在所有质量维度上均显著优于基线方法，生成的演示接近人类专家标准。PREVAL与人类判断表现出强相关性，验证了其作为评估演示质量的可靠自动化工具的有效性。
英文摘要：
Automated generation of high-quality media presentations is challenging, requiring robust content extraction, narrative planning, visual design, and overall quality optimization. Existing methods often produce presentations with logical inconsistencies and suboptimal layouts, thereby struggling to meet professional standards. To address these challenges, we introduce RCPS (Reflective Coherent Presentation Synthesis), a novel framework integrating three key components: (1) Deep Structured Narrative Planning; (2) Adaptive Layout Generation; (3) an Iterative Optimization Loop. Additionally, we propose PREVAL, a preference-based evaluation framework employing rationale-enhanced multi-dimensional models to assess presentation quality across Content, Coherence, and Design. Experimental results demonstrate that RCPS significantly outperforms baseline methods across all quality dimensions, producing presentations that closely approximate human expert standards. PREVAL shows strong correlation with human judgments, validating it as a reliable automated tool for assessing presentation quality.
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。
