TEMU-VTOFF

<div align="center"> <h1 align="center">TEMU-VTOFF</h1> <h3 align="center">Text-Enhanced MUlti-category Virtual Try-Off</h3> </div> <div align="center"> <picture> <source srcset="/davidelobba/TEMU-VTOFF/resolve/main/teaser.png" media="(prefers-color-scheme: dark)"> <img src="/davidelobba/TEMU-VTOFF/resolve/main/teaser.png" width="75%" alt="TEMU-VTOFF Teaser"> </source> </picture> </div> <div align="center">

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals Davide Lobba^1,2,*, Fulvio Sanguigni^2,3,*, Bin Ren^1,2, Marcella Cornia³, Rita Cucchiara³, Nicu Sebe¹ ¹University of Trento, ²University of Pisa, ³University of Modena and Reggio Emilia ^* Equal contribution

</div> <div align="center"> <a href="https://arxiv.org/abs/2505.21062" style="margin: 0 2px;"> <img src="https://img.shields.io/badge/Paper-Arxiv_2505.21062-darkred.svg" alt="Paper"> </a> <a href="https://temu-vtoff-page.github.io/" style="margin: 0 2px;"> <img src='https://img.shields.io/badge/Webpage-Project-silver?style=flat&logo=&logoColor=orange' alt='Project Webpage'> </a> <a href="https://github.com/davidelobba/TEMU-VTOFF" style="margin: 0 2px;"> <img src="https://img.shields.io/badge/GitHub-Repo-blue.svg?logo=github" alt="GitHub Repository"> </a> <!-- The Hugging Face model badge will be automatically displayed on the model page --> </div>

💡 Model Description

TEMU-VTOFF is a novel dual-DiT (Diffusion Transformer) architecture designed for the Virtual Try-Off task: generating in-shop images of garments worn by a person. By combining a pretrained feature extractor with a text-enhanced generation module, our method can handle occlusions, multiple garment categories, and ambiguous appearances. It further refines generation fidelity via a feature alignment module based on DINOv2.

This model is based on stabilityai/stable-diffusion-3-medium-diffusers. The uploaded weights correspond to the finetuned feature extractor and the VTOFF DiT module.

✨ Key Features

Our contribution can be summarized as follows:

• 🎯 Multi-Category Try-Off. We present a unified framework capable of handling multiple garment types (upper-body, lower-body, and full-body clothes) without requiring category-specific pipelines.
• 🔗 Multimodal Hybrid Attention. We introduce a novel attention mechanism that integrates garment textual descriptions into the generative process by linking them with person-specific features. This helps the model synthesize occluded or ambiguous garment regions more accurately.
• ⚡ Garment Aligner Module. We design a lightweight aligner that conditions generation on clean garment images, replacing conventional denoising objectives. This leads to better alignment consistency on the overall dataset and preserves more precise visual retention.
• 📊 Extensive experiments. Experiments on the Dress Code and VITON-HD datasets demonstrate that TEMU-VTOFF outperforms prior methods in both the quality of generated images and alignment with the target garment, highlighting its strong generalization capabilities.