DressCode：从文本自回归地缝制和生成服装 指南

DressCode: Autoregressively Sewing and Generating Garments from Text Guidance

January 29, 2024

作者: Kai He, Kaixin Yao, Qixuan Zhang, Jingyi Yu, Lingjie Liu, Lan Xu

cs.AI

摘要

服装在人类外表中的重要作用凸显了服装数字化对数字人类创作的重要性。最近在3D内容创作方面的进展对数字人类创作至关重要。然而，通过文本指导生成服装的技术仍处于起步阶段。我们引入了一种文本驱动的3D服装生成框架，名为DressCode，旨在为新手民主化设计，并在时尚设计、虚拟试穿和数字人类创作领域具有巨大潜力。在我们的框架中，我们首先介绍了SewingGPT，这是一种基于GPT的架构，将交叉注意力与文本条件嵌入相结合，以生成带有文本指导的缝纫图案。我们还定制了一个预训练的Stable Diffusion，用于生成高质量、基于瓷砖的PBR纹理。通过利用大型语言模型，我们的框架通过自然语言交互生成CG友好的服装。我们的方法还促进了图案完成和纹理编辑，通过用户友好的交互简化了设计师的流程。通过全面评估和与其他最先进方法的比较，我们的方法展示了最佳质量，并与输入提示对齐。用户研究进一步验证了我们高质量的渲染结果，突显了其在生产环境中的实用性和潜力。

English

Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. For our framework, we first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We also tailored a pre-trained Stable Diffusion for high-quality, tile-based PBR texture generation. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. Our method also facilitates pattern completion and texture editing, simplifying the process for designers by user-friendly interaction. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases the best quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings.