DressCode：從文本自回歸地裁剪和生成服裝 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

服裝在人類外表中的重要角色凸顯了對於數位人類創建的服裝數位化的重要性。最近在3D內容創建方面的進展對於數位人類的創建至關重要。然而，從文本指導生成服裝仍處於起步階段。我們引入了一個以文本驅動的3D服裝生成框架，名為DressCode，旨在為新手民主化設計，並在時尚設計、虛擬試穿和數位人類創建方面具有巨大潛力。對於我們的框架，我們首先介紹了SewingGPT，這是一個基於GPT的架構，整合了交叉注意力和文本條件嵌入，以生成帶有文本指導的縫紉圖案。我們還為高質量、基於瓷磚的PBR紋理生成定制了一個預訓練的Stable Diffusion。通過利用大型語言模型，我們的框架通過自然語言交互生成CG友好的服裝。我們的方法還促進了圖案完成和紋理編輯，通過用戶友好的交互簡化了設計師的流程。通過全面評估和與其他最先進方法的比較，我們的方法展示了最佳的質量和與輸入提示的對齊。用戶研究進一步驗證了我們高質量的渲染結果，突顯了其在生產環境中的實用性和潛力。

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.