场景布置（Mise-en-Scène）：用于人机协同设计共创的扩散Transformer中隐式布局的涌现
Mise-en-Scène: Implicit Layout Emergence in Diffusion Transformers for Human-AI Design Co-Creation
浏览论文内容
中文总结 AI 辅助
本文提出Mise-en-Scène框架，通过微调扩散Transformer实现隐式布局涌现，结合匹配放置步骤保证素材保真度，在PrismLayersPlus基准上生成的设计感知质量显著优于现有方法。
中文摘要 AI 辅助
从用户提供的元素自动生成平面设计，既需要整体构图的连贯性，又要精确保留每个素材。现有方法通过语言模型预测显式边界框坐标作为布局，再将素材粘贴到对应位置，这种方式将空间规划与视觉合成分离，易产生僵硬、比例失调的构图。我们转而探究布局是否能在预训练的图像编辑扩散Transformer中隐式涌现。本文提出Mise-en-Scène，这是一个两阶段框架：第一阶段，通过少量精选LoRA（低秩适配）微调的扩散Transformer生成完整设计草稿，其中元素的排列与渲染画布共同涌现；第二阶段，采用确定性匹配放置步骤，将原始高分辨率素材移动到草稿位置，保证素材的精确保真度，生成可编辑的分层设计，供设计师进一步优化，而非仅输出平面图像。值得注意的是，仅需对预训练Transformer进行最小程度的适配即可满足需求，无需为多元素生成引入常用的专用条件机制。在大规模PrismLayersPlus基准测试中，Mise-en-Scène生成的设计在感知质量上与真实值最为接近，大幅优于LLM布局规划器和专用布局Transformer，而我们的匹配放置阶段则缩小了与真实合成图的剩余保真度差距。
英文摘要
Automating graphic design synthesis from user-provided elements requires both a coherent overall composition and the exact preservation of each asset. Existing methods predict a layout as explicit bounding-box coordinates with a language model and then paste the assets into it, which separates spatial planning from visual synthesis and tends to produce rigid, mis-scaled compositions. We instead ask whether the layout can emerge implicitly inside a pretrained image-editing diffusion transformer. We present Mise-en-Scène, a two-stage framework. In the first stage, a diffusion transformer adapted with a small, knockout-selected LoRA drafts a complete design in which the arrangement of the elements emerges jointly with the rendered canvas. In the second stage, a deterministic match-and-place step moves the original high-resolution assets to the drafted positions, which guarantees exact asset fidelity and yields an editable, layered design that a designer can keep refining rather than a flat image. Notably, a minimal adaptation of the pretrained transformer already suffices, without the specialized conditioning machinery commonly introduced for multi-element generation. On the large-scale PrismLayersPlus benchmark, the designs produced by Mise-en-Scène are the closest to the ground truth in perceived quality among all compared methods, by a wide margin over both an LLM layout planner and a specialized layout transformer, while our match-and-place stage bridges the remaining fidelity gap to the ground-truth composites.
发表机构
- Canva Research（Canva研究院）
机构由 AI 辅助整理，请以论文原文为准。
