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

TL;DR

GO-MLVTON is a pioneering multi-layer virtual try-on system that models occlusion relationships between garments, enabling realistic layered dressing with high-quality results using diffusion models.

Contribution

It introduces the first multi-layer VTON method with occlusion learning, garment morphing, and fitting modules, along with a new dataset and evaluation metric.

Findings

Achieves state-of-the-art multi-layer try-on quality

Effectively models occlusion relationships between garments

Demonstrates superior realism and layering in results

Abstract

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/.