PosterCopilot: 向专业图形设计中的布局推理与可控编辑迈进
PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design
AI总结：
PosterCopilot通过三阶段训练策略和完整工作流程，实现专业图形设计中布局推理与可控编辑的提升。
摘要：
图形设计是现代视觉传播的基础，是促进文化和商业活动的重要媒介。近期的进展探索了利用大多模态模型（LMMs）自动化这一过程，但现有方法往往产生几何不准确的布局，并缺乏专业工作流程中所需的迭代、分层编辑能力。为了解决这些限制，我们提出了PosterCopilot框架，该框架在专业图形设计中推进布局推理和可控编辑。具体而言，我们引入了一种渐进的三阶段训练策略，使LMMs具备几何理解和布局设计的审美推理能力，包括扰动监督微调、用于视觉-现实对齐的强化学习以及基于审美反馈的强化学习。此外，我们开发了一个完整的流程，将训练后的LMM设计模型与生成模型结合，使能够实现分层可控、迭代编辑，以精确元素细化的同时保持全局视觉一致性。广泛的实验表明，PosterCopilot实现了几何准确且审美优越的布局，提供了前所未有的可控性，以支持专业迭代设计。
英文摘要：
Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these limitations, we present PosterCopilot, a framework that advances layout reasoning and controllable editing for professional graphic design. Specifically, we introduce a progressive three-stage training strategy that equips LMMs with geometric understanding and aesthetic reasoning for layout design, consisting of Perturbed Supervised Fine-Tuning, Reinforcement Learning for Visual-Reality Alignment, and Reinforcement Learning from Aesthetic Feedback. Furthermore, we develop a complete workflow that couples the trained LMM-based design model with generative models, enabling layer-controllable, iterative editing for precise element refinement while maintaining global visual consistency. Extensive experiments demonstrate that PosterCopilot achieves geometrically accurate and aesthetically superior layouts, offering unprecedented controllability for professional iterative design.
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。
