arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.07240cs.CVcs.GR
收藏

FabricGen: 基于微结构的编织材料生成

FabricGen: Microstructure-Aware Woven Fabric Generation

Nankai University(南开大学);Nanjing University(南京大学)

Yingjie Tang, Di Luo, Zixiong Wang, Xiaoli Ling, jian Yang, Beibei Wang

AI总结:

FabricGen通过分解宏观纹理与微观编织模式,结合预训练扩散模型和专用语言模型,实现高质量编织材料的生成。

摘要:

编织材料广泛应用于渲染应用,但设计逼真的示例通常需要多个阶段,需要对编织原理和纹理创作有专业知识。最近的进展探索了扩散模型以简化此过程;然而,预训练的扩散模型往往难以生成符合编织规则的复杂纱线级细节。为此,我们提出了FabricGen,一种端到端框架,用于从文本描述生成高质量的编织材料。我们方法的关键见解是将宏观尺度纹理和微观尺度编织图案分解开来。为了生成不受微观结构影响的宏观尺度纹理,我们对预训练的扩散模型进行微调,使用收集的无微观结构织物数据集。至于微观尺度的编织图案,我们开发了一种增强的程序几何模型,能够合成自然的纱线级几何结构,包括纱线滑动和飞散纤维。该程序模型由一个专门的大型语言模型WeavingLLM驱动,该模型在注释的格式化编织草图数据集上进行微调,并通过领域特定的织物专业知识进行提示微调。通过微调和提示微调,WeavingLLM学会从文本提示中设计编织草图和织物参数,使程序模型能够生成多样化的编织图案,符合编织原则。生成的宏观尺度纹理,加上微观尺度的几何结构,可用于织物渲染。因此,我们的框架生成的材料比先前的生成模型具有显著更丰富的细节和真实感。

英文摘要:

Woven fabric materials are widely used in rendering applications, yet designing realistic examples typically involves multiple stages, requiring expertise in weaving principles and texture authoring. Recent advances have explored diffusion models to streamline this process; however, pre-trained diffusion models often struggle to generate intricate yarn-level details that conform to weaving rules. To address this, we present FabricGen, an end-to-end framework for generating high-quality woven fabric materials from textual descriptions. A key insight of our method is the decomposition of macro-scale textures and micro-scale weaving patterns. To generate macro-scale textures free from microstructures, we fine-tune pre-trained diffusion models on a collected dataset of microstructure-free fabrics. As for micro-scale weaving patterns, we develop an enhanced procedural geometric model capable of synthesizing natural yarn-level geometry with yarn sliding and flyaway fibers. The procedural model is driven by a specialized large language model, WeavingLLM, which is fine-tuned on an annotated dataset of formatted weaving drafts, and prompt-tuned with domain-specific fabric expertise. Through fine-tuning and prompt tuning, WeavingLLM learns to design weaving drafts and fabric parameters from textual prompts, enabling the procedural model to produce diverse weaving patterns that stick to weaving principles. The generated macro-scale texture, along with the micro-scale geometry, can be used for fabric rendering. Consequently, our framework produces materials with significantly richer detail and realism compared to prior generative models.

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。

↑