GO-MLVTON: Garment Occlusion-Aware Multi-Layer Virtual Try-On with Diffusion Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Yang, Deng, Yunze, Zhang, Yige, Xiao, Yanjie, Ou, Youkun, Hu, Wenhao, Li, Mingchao, Feng, Bin, Liu, Wenyu, Zheng, Dandan, Chen, Jingdong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918328474271744
author Yu, Yang
Deng, Yunze
Zhang, Yige
Xiao, Yanjie
Ou, Youkun
Hu, Wenhao
Li, Mingchao
Feng, Bin
Liu, Wenyu
Zheng, Dandan
Chen, Jingdong
author_facet Yu, Yang
Deng, Yunze
Zhang, Yige
Xiao, Yanjie
Ou, Youkun
Hu, Wenhao
Li, Mingchao
Feng, Bin
Liu, Wenyu
Zheng, Dandan
Chen, Jingdong
contents Existing image-based virtual try-on (VTON) methods primarily focus on single-layer or multi-garment VTON, neglecting multi-layer VTON (ML-VTON), which involves dressing multiple layers of garments onto the human body with realistic deformation and layering to generate visually plausible outcomes. The main challenge lies in accurately modeling occlusion relationships between inner and outer garments to reduce interference from redundant inner garment features. To address this, we propose GO-MLVTON, the first multi-layer VTON method, introducing the Garment Occlusion Learning module to learn occlusion relationships and the StableDiffusion-based Garment Morphing & Fitting module to deform and fit garments onto the human body, producing high-quality multi-layer try-on results. Additionally, we present the MLG dataset for this task and propose a new metric named Layered Appearance Coherence Difference (LACD) for evaluation. Extensive experiments demonstrate the state-of-the-art performance of GO-MLVTON. Project page: https://upyuyang.github.io/go-mlvton/.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13524
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GO-MLVTON: Garment Occlusion-Aware Multi-Layer Virtual Try-On with Diffusion Models
Yu, Yang
Deng, Yunze
Zhang, Yige
Xiao, Yanjie
Ou, Youkun
Hu, Wenhao
Li, Mingchao
Feng, Bin
Liu, Wenyu
Zheng, Dandan
Chen, Jingdong
Computer Vision and Pattern Recognition
Existing image-based virtual try-on (VTON) methods primarily focus on single-layer or multi-garment VTON, neglecting multi-layer VTON (ML-VTON), which involves dressing multiple layers of garments onto the human body with realistic deformation and layering to generate visually plausible outcomes. The main challenge lies in accurately modeling occlusion relationships between inner and outer garments to reduce interference from redundant inner garment features. To address this, we propose GO-MLVTON, the first multi-layer VTON method, introducing the Garment Occlusion Learning module to learn occlusion relationships and the StableDiffusion-based Garment Morphing & Fitting module to deform and fit garments onto the human body, producing high-quality multi-layer try-on results. Additionally, we present the MLG dataset for this task and propose a new metric named Layered Appearance Coherence Difference (LACD) for evaluation. Extensive experiments demonstrate the state-of-the-art performance of GO-MLVTON. Project page: https://upyuyang.github.io/go-mlvton/.
title GO-MLVTON: Garment Occlusion-Aware Multi-Layer Virtual Try-On with Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.13524