Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On

TL;DR

Cloth2Tex is a self-supervised pipeline that efficiently generates high-quality, structurally consistent textures for 3D garments from simple inputs, supporting high-fidelity inpainting and outperforming existing methods.

Contribution

We introduce Cloth2Tex, a novel self-supervised method that automates texture generation for 3D garments, reducing manual effort and enhancing quality with inpainting capabilities.

Findings

Cloth2Tex produces high-quality, consistent texture maps.

It outperforms traditional warping-based methods in visual quality.

Supports high-fidelity texture inpainting with diffusion models.

Abstract

Fabricating and designing 3D garments has become extremely demanding with the increasing need for synthesizing realistic dressed persons for a variety of applications, e.g. 3D virtual try-on, digitalization of 2D clothes into 3D apparel, and cloth animation. It thus necessitates a simple and straightforward pipeline to obtain high-quality texture from simple input, such as 2D reference images. Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process. We propose a novel method, called Cloth2Tex, which eliminates the human burden in this process. Cloth2Tex is a self-supervised method that generates texture maps with reasonable layout and structural consistency. Another key feature of Cloth2Tex is that it can be used to support high-fidelity texture inpainting. This is done by combining Cloth2Tex with a prevailing latent diffusion model. We evaluate our approach both qualitatively and quantitatively and demonstrate that Cloth2Tex can generate high-quality texture maps and achieve the best visual effects in comparison to other methods. Project page: tomguluson92.github.io/projects/cloth2tex/