TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zhenchen, Xu, Yanwu, Wang, Zhaoqing, Liu, Feng, Liu, Tongliang, Gong, Mingming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929752161386496
author Wan, Zhenchen
Xu, Yanwu
Wang, Zhaoqing
Liu, Feng
Liu, Tongliang
Gong, Mingming
author_facet Wan, Zhenchen
Xu, Yanwu
Wang, Zhaoqing
Liu, Feng
Liu, Tongliang
Gong, Mingming
contents Recent advancements in Virtual Try-On (VTO) have demonstrated exceptional efficacy in generating realistic images and preserving garment details, largely attributed to the robust generative capabilities of text-to-image (T2I) diffusion backbones. However, the T2I models that underpin these methods have become outdated, thereby limiting the potential for further improvement in VTO. Additionally, current methods face notable challenges in accurately rendering text on garments without distortion and preserving fine-grained details, such as textures and material fidelity. The emergence of Diffusion Transformer (DiT) based T2I models has showcased impressive performance and offers a promising opportunity for advancing VTO. Directly applying existing VTO techniques to transformer-based T2I models is ineffective due to substantial architectural differences, which hinder their ability to fully leverage the models' advanced capabilities for improved text generation. To address these challenges and unlock the full potential of DiT-based T2I models for VTO, we propose TED-VITON, a novel framework that integrates a Garment Semantic (GS) Adapter for enhancing garment-specific features, a Text Preservation Loss to ensure accurate and distortion-free text rendering, and a constraint mechanism to generate prompts by optimizing Large Language Model (LLM). These innovations enable state-of-the-art (SOTA) performance in visual quality and text fidelity, establishing a new benchmark for VTO task. Project page: https://zhenchenwan.github.io/TED-VITON/
format Preprint
id arxiv_https___arxiv_org_abs_2411_17017
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On
Wan, Zhenchen
Xu, Yanwu
Wang, Zhaoqing
Liu, Feng
Liu, Tongliang
Gong, Mingming
Computer Vision and Pattern Recognition
Recent advancements in Virtual Try-On (VTO) have demonstrated exceptional efficacy in generating realistic images and preserving garment details, largely attributed to the robust generative capabilities of text-to-image (T2I) diffusion backbones. However, the T2I models that underpin these methods have become outdated, thereby limiting the potential for further improvement in VTO. Additionally, current methods face notable challenges in accurately rendering text on garments without distortion and preserving fine-grained details, such as textures and material fidelity. The emergence of Diffusion Transformer (DiT) based T2I models has showcased impressive performance and offers a promising opportunity for advancing VTO. Directly applying existing VTO techniques to transformer-based T2I models is ineffective due to substantial architectural differences, which hinder their ability to fully leverage the models' advanced capabilities for improved text generation. To address these challenges and unlock the full potential of DiT-based T2I models for VTO, we propose TED-VITON, a novel framework that integrates a Garment Semantic (GS) Adapter for enhancing garment-specific features, a Text Preservation Loss to ensure accurate and distortion-free text rendering, and a constraint mechanism to generate prompts by optimizing Large Language Model (LLM). These innovations enable state-of-the-art (SOTA) performance in visual quality and text fidelity, establishing a new benchmark for VTO task. Project page: https://zhenchenwan.github.io/TED-VITON/
title TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17017