DOGS: Design-Space Sampling for Prompt-Driven Logo Generation

查看原文 / View Original 编辑 / Edit

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.10760 (cs) [Submitted on 7 Oct 2026] Title: DOGS: Design-Space Sampling for Prompt-Driven Logo Generation Authors: Ganyu Zou, Chen Dai, Nathan Self, Kevin Piper, Ramachandra Rao Seethiraju, Karthik Shyamsunder, Chang-Tien Lu, Naren Ramakrishnan.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.10760 (cs) [提交于 2026 年 10 月 7 日] 标题：DOGS：用于提示驱动标志生成的空间采样设计作者：Ganyu Zou, Chen Dai, Nathan Self, Kevin Piper, Ramachandra Rao Seethiraju, Karthik Shyamsunder, Chang-Tien Lu, Naren Ramakrishnan。

Abstract: Prompt optimization for text-to-image (T2I) generation has been pursued almost entirely as text rewriting, in which a short user brief is expanded into a longer, model-preferred token sequence. We argue that such a language-space formulation is ill-suited to structured visual design tasks such as logo creation, where a one-line brief leaves most design decisions unspecified.

摘要：文本到图像（T2I）生成的提示优化几乎完全被视为文本重写，即将简短的用户简介扩展为更长的、模型偏好的标记序列。我们认为，这种语言空间公式并不适用于标志创作等结构化视觉设计任务，因为一行简介无法明确大多数设计决策。

These decisions depend on relational priors that a linear sequence cannot encode, and they leave an uncontrolled channel through which protected marks may be reproduced. We therefore recast logo prompting as sampling within a structured design space, and instantiate this idea as DOGS (Design-space prompting with an Originality-aware GFlowNet Sampler).

这些决策依赖于线性序列无法编码的关系先验，并且它们留下了一个不受控制的通道，通过该通道可能会复制受保护的商标。因此，我们将标志提示重构为结构化设计空间内的采样，并将这一想法实例化为 DOGS（具有原创性感知 GFlowNet 采样器的设计空间提示）。

From a large corpus of real-world logos, we mine a typed, graph-structured design grammar whose edges record empirical co-occurrence. A GFlowNet sampler then generates design graphs with probability proportional to a terminal reward that combines recognizability, aesthetics, and corpus-relative originality.

从大量的现实世界标志语料库中，我们挖掘出一种类型化的、图结构的设计语法，其边记录了经验共现。随后，GFlowNet 采样器以与结合了可识别性、美学和语料库相对原创性的终端奖励成正比的概率生成设计图。

Every slot draws only from a closed design-level vocabulary, and any infringement-inducing or harmful token is removed during parsing. The originality reward further penalizes proximity to existing logos, thereby incorporating infringement avoidance into the method by construction.

每个槽位仅从封闭的设计级词汇表中提取，任何导致侵权或有害的标记都会在解析过程中被删除。原创性奖励进一步惩罚与现有标志的相似度，从而在构建方法时将避免侵权纳入其中。

On two open-source renderers and against nine baselines, DOGS produces logos that are more recognizable and aesthetic, substantially more diverse, and far less prone to trademark infringement.

在两个开源渲染器上并针对九个基准进行测试，DOGS 生成的标志更具可识别性和美感，多样性显著提高，且更不容易产生商标侵权。