首个支持多层衣物试穿的生成方法，解决内外衣遮挡关系建模难题。
GO-MLVTON: Garment Occlusion-Aware Multi-Layer Virtual Try-On with Diffusion Models
- 引入遮挡感知模块学习衣物间遮挡关系，减少特征干扰。
- 基于Stable Diffusion实现衣物形变与贴合，生成高质量多层试穿图。
- 构建新数据集和评估指标，适合服装生成与数字人研究者参考。
现有基于图像的虚拟试穿方法主要关注单层或多件衣物试穿，忽视了涉及多层衣物穿戴、真实形变与叠穿效果的多层虚拟试穿（ML-VTON）。其核心挑战在于准确建模内层与外层衣物间的遮挡关系，以减少冗余内层特征的干扰。为此，我们提出首个多层虚拟试穿方法GO-MLVTON，引入衣物遮挡学习模块以建模遮挡关系，并采用基于StableDiffusion的衣物形变与贴合模块，实现衣物在人体上的形变与适配，生成视觉上合理的多层试穿结果。此外，我们构建了用于该任务的MLG数据集，并提出了新的评估指标层间外观一致性差异（LACD）。大量实验表明，GO-MLVTON达到当前最优性能。项目页面：https://upyuyang.github.io/go-mlvton/
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。