让AI按步骤分层生成设计，更贴近真实创作过程。
Step-by-step Layered Design Generation
- 将设计修改视为逐层原子变化，每步响应具体指令
- 在新构建的数据集上优于现有方法，生成更连贯的设计序列
- 适合研究人机协同设计、可控生成的开发者
设计生成本质上是一个逐步进行的过程，设计师通过一系列精细调整不断优化作品。然而，现有方法大多将设计合成视为单步生成问题，严重低估了创作过程的内在复杂性。为此，我们提出新的问题设定——分步分层设计生成，要求机器学习模型根据设计师给出的一系列指令逐步生成设计。借助多模态大模型的进展，我们提出了SLEDGE（Step-by-step LayEred Design GEnerator），将每次设计更新建模为相对于前一状态的原子化、分层变化，并严格遵循指令。为支持新任务，我们构建了一个包含数据集与基准测试的新评估体系。大量实验分析和与先进方法的对比表明，本方法在生成连贯设计序列方面具有显著优势。我们希望本工作能引发对该务实且未充分探索研究方向的关注。
原文摘要 · Abstract (English)
Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.
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。