Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Custom Cloth Creation and Virtual Try-on for Everyone

Pei Chen, Heng Wang, Sainan Sun, Zhiyuan Chen, Zhenkun Liu, Shuhua Cao, Li Yang, Minghui Yang

TL;DR

The paper addresses the challenge of scalable virtual clothing design for avatars by combining UV-map texture editing with AI-generated textures, enabling both professionals and ordinary users to customize outfits. It integrates garment part annotation, a Text-to-Image model with LoRA finetuning, and three editing modes to produce region-specific textures and logos. An Alipay app integration demonstrates practical deployment for end users, with saved outfits in a virtual wardrobe. The work promises lower production costs and faster iteration, supporting wider metaverse adoption.

Abstract

This demo showcases a simple tool that utilizes AIGC technology, enabling both professional designers and regular users to easily customize clothing for their digital avatars. Customization options include changing clothing colors, textures, logos, and patterns. Compared with traditional 3D modeling processes, our approach significantly enhances efficiency and interactivity and reduces production costs.

Custom Cloth Creation and Virtual Try-on for Everyone

TL;DR

The paper addresses the challenge of scalable virtual clothing design for avatars by combining UV-map texture editing with AI-generated textures, enabling both professionals and ordinary users to customize outfits. It integrates garment part annotation, a Text-to-Image model with LoRA finetuning, and three editing modes to produce region-specific textures and logos. An Alipay app integration demonstrates practical deployment for end users, with saved outfits in a virtual wardrobe. The work promises lower production costs and faster iteration, supporting wider metaverse adoption.

Abstract

This demo showcases a simple tool that utilizes AIGC technology, enabling both professional designers and regular users to easily customize clothing for their digital avatars. Customization options include changing clothing colors, textures, logos, and patterns. Compared with traditional 3D modeling processes, our approach significantly enhances efficiency and interactivity and reduces production costs.
Paper Structure (7 sections, 5 figures)

This paper contains 7 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Method
  3. Clothing Parts Annotation
  4. Text-to-Image Generation Model
  5. Clothing Texture Editing
  6. Demonstraion
  7. Conclusion

Figures (5)

  • Figure 1: Texture Editing Example. The main image shows the clothing after texture editing, with the original clothing shown in the bottom right or bottom left corner.
  • Figure 2: Three Modes of Clothing Texture Editing. Here are three editing modes that meet different types of custom clothing requirements: localized color or texture modifications, logo printing.
  • Figure 3: Three Modes of Clothing Texture Editing. Here are three editing modes that meet different types of custom clothing requirements: localized color or texture modifications, logo printing.
  • Figure 4: Professional artists use 3D design software to annotate different parts of the clothing manually and generate corresponding mask images of the clothing's UV maps.
  • Figure 5: Customized Clothing Creation on Alipay app. Users can use our tool within the Alipay app to create clothing for their digital avatars.