DressCode: Autoregressively Sewing and Generating Garments from Text Guidance

TL;DR

DressCode is a novel framework that enables text-guided 3D garment creation, combining sewing pattern generation and texture rendering to facilitate digital fashion design and virtual human creation.

Contribution

It introduces SewingGPT for text-conditioned sewing pattern generation and adapts Stable Diffusion for PBR texture synthesis, advancing text-driven 3D garment generation.

Findings

Outperforms state-of-the-art methods in quality and prompt alignment

Enables pattern completion and texture editing for flexible design

User studies confirm high-quality, practical results

Abstract

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/.