基于 strand 的发型生成：结合大型重建模型与多模态模型
Strand-based Hairstyle Generation via Large Reconstruction and Multimodal Models
浏览论文内容
中文总结 AI 辅助
该研究提出一种结合 LRMs、LMMs 与经典几何处理的自动流程，可从单视图图像快速生成高质量、适配生产的各类基于 strand 的发型，适用于现代数字人工作流。
中文摘要 AI 辅助
在当前的生产流程中，创建高质量的基于 strand 的发型仍高度依赖熟练艺术家和耗时的手动创作，这使得该过程成本高昂且难以规模化。现有的基于学习的方法已在图像驱动的头发重建方面取得进展，但通常需要大量多样化的训练数据集，难以泛化到发髻和马尾辫等复杂发型，且通常采用与基于 strand 的建模、编辑和模拟不直接兼容的表示形式。我们提出了一种新颖的自动流程，结合大型重建模型（Large Reconstruction Models, LRMs）、大型多模态模型（Large Multimodal Models, LMMs）和经典几何处理的能力，从单视图图像生成高质量的基于 strand 的发型。我们的方法无需特定任务训练或数据收集即可生成详细的、可用于生产的 strand 几何，能够处理多种发型，包括直发和卷发、短发和长发，以及马尾辫和发髻等具有挑战性的结构化发型。在这些多样化的示例中，我们的方法仅在几分钟内即可生成视觉上有吸引力的 strand 级重建，非常适合集成到现代数字人工作流中。
英文摘要
Creating high-quality strand-based hairstyles in current production pipelines remains heavily dependent on skilled artists and time-consuming manual authoring, making it costly and difficult to scale. Existing learning-based methods have advanced image-driven hair reconstruction, but typically require large, diverse training datasets, struggle to generalize to complex styles such as buns and ponytails, and often operate in representations that are not directly compatible with strand-based modeling, editing, and simulation. We present a novel automatic pipeline that combines the capabilities of Large Reconstruction Models (LRMs), Large Multimodal Models (LMMs), and classical geometry processing to generate high-quality strand-based hairstyles from single-view images. Our approach produces detailed, production-ready strand geometry without task-specific training or data collection and can handle a wide variety of hairstyles, including straight and curly hair, short and long styles, and challenging structured configurations such as ponytails and buns. Across this diverse set of examples, our method generates visually compelling strand-level reconstructions within only a few minutes, making it well-suited for integration into modern digital human workflows.
