Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Angang, Deng, Fang, Chen, Hao, Chen, Zhongjian, Li, Junyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480290422784
author Zhang, Angang
Deng, Fang
Chen, Hao
Chen, Zhongjian
Li, Junyan
author_facet Zhang, Angang
Deng, Fang
Chen, Hao
Chen, Zhongjian
Li, Junyan
contents While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF), which aims to reconstruct canonical garment templates from dressed humans, remains critically underexplored and lacks systematic investigation. Existing works predominantly treat them as isolated tasks: VTON focuses on garment dressing while VTOFF addresses garment extraction, thereby neglecting their complementary symmetry. To bridge this fundamental gap, we propose the Two-Way Garment Transfer Model (TWGTM), to the best of our knowledge, the first unified framework for joint clothing-centric image synthesis that simultaneously resolves both mask-guided VTON and mask-free VTOFF through bidirectional feature disentanglement. Specifically, our framework employs dual-conditioned guidance from both latent and pixel spaces of reference images to seamlessly bridge the dual tasks. On the other hand, to resolve the inherent mask dependency asymmetry between mask-guided VTON and mask-free VTOFF, we devise a phased training paradigm that progressively bridges this modality gap. Extensive qualitative and quantitative experiments conducted across the DressCode and VITON-HD datasets validate the efficacy and competitive edge of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04551
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
Zhang, Angang
Deng, Fang
Chen, Hao
Chen, Zhongjian
Li, Junyan
Computer Vision and Pattern Recognition
While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF), which aims to reconstruct canonical garment templates from dressed humans, remains critically underexplored and lacks systematic investigation. Existing works predominantly treat them as isolated tasks: VTON focuses on garment dressing while VTOFF addresses garment extraction, thereby neglecting their complementary symmetry. To bridge this fundamental gap, we propose the Two-Way Garment Transfer Model (TWGTM), to the best of our knowledge, the first unified framework for joint clothing-centric image synthesis that simultaneously resolves both mask-guided VTON and mask-free VTOFF through bidirectional feature disentanglement. Specifically, our framework employs dual-conditioned guidance from both latent and pixel spaces of reference images to seamlessly bridge the dual tasks. On the other hand, to resolve the inherent mask dependency asymmetry between mask-guided VTON and mask-free VTOFF, we devise a phased training paradigm that progressively bridges this modality gap. Extensive qualitative and quantitative experiments conducted across the DressCode and VITON-HD datasets validate the efficacy and competitive edge of our proposed approach.
title Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.04551