從元素到設計：自動平面設計的分層方法 構圖

From Elements to Design: A Layered Approach for Automatic Graphic Design Composition

December 27, 2024

作者: Jiawei Lin, Shizhao Sun, Danqing Huang, Ting Liu, Ji Li, Jiang Bian

cs.AI

摘要

在這項研究中，我們探討從多模態圖形元素進行自動設計合成。儘管最近的研究已經為圖形設計開發了各種生成模型，但它們通常面臨以下限制：它們僅專注於某些子任務，並且遠未達到設計合成任務；在生成過程中，它們並未考慮圖形設計的階層信息。為了應對這些問題，我們將分層設計原則引入大型多模態模型（LMMs），並提出一種新方法，稱為LaDeCo，以完成這一具有挑戰性的任務。具體來說，LaDeCo 首先針對給定元素集執行層規劃，根據其內容將輸入元素劃分為不同的語義層。基於規劃結果，它隨後以分層方式預測控制設計合成的元素屬性，並將先前生成的層的渲染圖像包含在上下文中。通過這種具洞察力的設計，LaDeCo將困難的任務分解為更小的可管理步驟，使生成過程更加順暢和清晰。實驗結果證明了LaDeCo在設計合成中的有效性。此外，我們展示了LaDeCo在圖形設計中實現一些有趣的應用，如分辨率調整、元素填充、設計變化等。此外，它甚至在某些設計子任務中優於專門模型，而無需進行任務特定的訓練。

English

In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the generation process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, element filling, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training.