ChArtist：统一空间与主体控制生成图案化图表
ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
提出基于骨架的空间控制表示与 Spatially Gated Attention，用于在 DiT 中解耦空间结构与主体外观，可复用于需要同时控制布局和参考外观的生成任务。
原文依据 We introduce a skeleton-based spatial control representation. This representation encodes only the data-encoding information of the chart
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图案化图表是一种有效的视觉叙事媒介，它将视觉元素与数据图表无缝融合。然而，创建此类图像颇具挑战，因为视觉元素的灵活性与图表结构的刚性常常冲突。这一过程因此需要一种创造性的变形，同时保持数据忠实性与视觉美感。当前从自然图像中提取稠密结构线索（如边缘或深度图）的方法，不适合作为图案化图表生成的条件信号。我们提出 ChArtist，一种自动生成图案化图表的领域特定方法，提供两种不同的控制类型：1）与图表结构良好对齐的空间控制；2）尊重参考图像视觉特征的主体驱动控制。为实现这一目标，我们引入基于骨架的空间控制表示。该表示仅编码图表的数据编码信息，从而能够轻松融入参考视觉元素，而不受刚性轮廓约束。我们基于扩散 Transformer（DiT）实现该方法，并利用自适应位置编码机制来管理这两种控制。我们进一步引入空间门控注意力来调节空间控制与主体控制之间的交互。为支持预训练模型在此任务上的微调，我们创建了一个包含 30,000 个三元组（骨架、参考图像、图案化图表）的大规模数据集。我们还提出了一个统一的数据准确性指标，用于评估生成图表的数据忠实性。我们相信这项工作表明，当前生成模型能够通过超越通用条件转向任务特定表示，实现数据驱动的视觉叙事。代码和数据集将公开。项目页面：https://chartist-ai.github.io/。
英文原文摘要 1890 字符
A pictorial chart is an effective medium for visual storytelling, seamlessly integrating visual elements with data charts. However, creating such images is challenging because the flexibility of visual elements often conflicts with the rigidity of chart structures. This process thus requires a creative deformation that maintains both data faithfulness and visual aesthetics. Current methods that extract dense structural cues from natural images (e.g., edge or depth maps) are ill-suited as conditioning signals for pictorial chart generation. We present ChArtist, a domain-specific method for generating pictorial charts automatically, offering two distinct types of control: 1) spatial control that aligns well with the chart structure, and 2) subject-driven control that respects the visual characteristics of a reference image. To achieve this, we introduce a skeleton-based spatial control representation. This representation encodes only the data-encoding information of the chart, allowing for the easy incorporation of reference visuals without a rigid outline constraint. We implement our method based on the Diffusion Transformer (DiT) and leverage an adaptive position encoding mechanism to manage these two controls. We further introduce Spatially Gated Attention to modulate the interaction between spatial control and subject control. To support the fine-tuning of pre-trained models for this task, we created a large-scale dataset of 30,000 triplets (skeleton, reference image, pictorial chart). We also propose a unified data accuracy metric to evaluate the data faithfulness of the generated charts. We believe this work demonstrates that current generative models can achieve data-driven visual storytelling by moving beyond general-purpose conditions to task-specific representations. The code and dataset will be released. Project page: https://chartist-ai.github.io/.