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. We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We then tailor a pre-trained Stable Diffusion to generate tile-based Physically-based Rendering (PBR) textures for the garments. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. It also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases superior quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Our project page is https://IHe-KaiI.github.io/DressCode/.

翻译：摘要：服装在人类外观中扮演着重要角色，其数字化对于数字人类创作具有关键意义。近年来3D内容创作的进展为数字人类构建提供了重要支撑，然而基于文本引导的服装生成技术仍处于探索阶段。本文提出文本驱动的3D服装生成框架DressCode，旨在降低设计门槛，使非专业人士也能参与创作，并在时尚设计、虚拟试穿及数字人类构建领域展现巨大潜力。我们首先提出SewingGPT——一种基于GPT架构的模型，通过引入交叉注意力机制与文本条件嵌入，实现文本引导下的缝纫图案生成。随后，我们定制预训练的Stable Diffusion模型，为服装生成基于平铺的物理渲染纹理。通过融合大语言模型，本框架支持通过自然语言交互生成符合计算机图形学标准的服装，并实现图案补全与纹理编辑功能，以用户友好的交互方式简化设计流程。该框架允许创作者自由实验设计、将独特元素融入作品，从而激发创新。经全面评估及与现有最优方法的对比，本方法在生成质量与输入提示一致性方面均表现优异。用户研究进一步验证了其高质量渲染效果，凸显了在工业场景中的实用价值与潜力。项目主页：https://IHe-KaiI.github.io/DressCode/。