BBQ-to-Image: 数字边界框与颜色控制在大规模文本到图像模型中
BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models
AI总结:
BBQ-to-Image通过引入数字边界框和RGB三元组的直接条件生成,实现了对文本到图像模型中物体位置、大小和颜色的精确控制,提升了生成图像的准确性和可控性。
摘要:
文本到图像模型在真实感和可控性方面迅速发展,最近的方法利用长而详细的描述来支持精细生成。然而,仍存在一个基本参数缺口:现有模型依赖描述性语言,而专业工作流程需要对物体位置、大小和颜色进行精确的数值控制。在本文中,我们引入了BBQ,一种大规模文本到图像模型,它在统一的结构化文本框架中直接对数字边界框和RGB三元组进行条件生成。我们通过在带有参数注释的描述上训练,获得精确的空间和色度控制,而无需架构修改或推理时间优化。这还使直观的用户界面如物体拖动和颜色选择器成为可能,用精确且熟悉的控制取代模糊的迭代提示。在全面评估中,BBQ实现了强大的框对齐,并在最先进的基线之上提高了RGB颜色保真度。更广泛地说,我们的结果支持了一个新的范式,即用户意图被翻译成中间结构化语言,由一个基于流的变压器作为渲染器消耗,并自然地容纳数值参数。
英文摘要:
Text-to-image models have rapidly advanced in realism and controllability, with recent approaches leveraging long, detailed captions to support fine-grained generation. However, a fundamental parametric gap remains: existing models rely on descriptive language, whereas professional workflows require precise numeric control over object location, size, and color. In this work, we introduce BBQ, a large-scale text-to-image model that directly conditions on numeric bounding boxes and RGB triplets within a unified structured-text framework. We obtain precise spatial and chromatic control by training on captions enriched with parametric annotations, without architectural modifications or inference-time optimization. This also enables intuitive user interfaces such as object dragging and color pickers, replacing ambiguous iterative prompting with precise, familiar controls. Across comprehensive evaluations, BBQ achieves strong box alignment and improves RGB color fidelity over state-of-the-art baselines. More broadly, our results support a new paradigm in which user intent is translated into an intermediate structured language, consumed by a flow-based transformer acting as a renderer and naturally accommodating numeric parameters.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。