DuetSVG：基于内部视觉引导的统一多模态SVG生成
DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance
AI总结：
DuetSVG通过端到端生成图像和SVG标记，结合内部视觉引导提升SVG生成质量，实现视觉忠实与语义一致的统一多模态生成。
摘要：
近期基于视觉-语言模型（VLM）的方法在SVG生成上取得了显著成果。然而，由于它们只生成文本且在解码过程中缺乏视觉信号，它们往往在处理复杂语义时遇到困难，无法生成视觉上吸引人或几何上一致的SVG。我们引入了DuetSVG，一个统一的多模态模型，能够端到端地联合生成图像标记和对应的SVG标记。DuetSVG是在图像和SVG数据集上训练的。在推理过程中，我们应用了一种新的测试时间缩放策略，利用模型本身的视觉预测作为引导，以提高SVG解码质量。大量实验表明，我们的方法在广泛的应用中优于现有方法，能够生成视觉忠实、语义一致且语法整洁的SVG。
英文摘要：
Recent vision-language model (VLM)-based approaches have achieved impressive results on SVG generation. However, because they generate only text and lack visual signals during decoding, they often struggle with complex semantics and fail to produce visually appealing or geometrically coherent SVGs. We introduce DuetSVG, a unified multimodal model that jointly generates image tokens and corresponding SVG tokens in an end-to-end manner. DuetSVG is trained on both image and SVG datasets. At inference, we apply a novel test-time scaling strategy that leverages the model's native visual predictions as guidance to improve SVG decoding quality. Extensive experiments show that our method outperforms existing methods, producing visually faithful, semantically aligned, and syntactically clean SVGs across a wide range of applications.
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。
