解决虚拟试衣中衣物形变与皮肤修复难题，提升换装自然度。
Clothing agnostic Pre-inpainting Virtual Try-ON
- 用多类别掩码与皮肤膨胀预处理，增强人体结构一致性。
- 短袖换装准确率达92.5%，比Leffa提升15.4%。
- 适配多种扩散模型，适用于电商与虚拟形象设计。
随着深度学习技术的发展，虚拟试衣在电商、时尚和娱乐领域具有重要应用价值。近期提出的Leffa技术虽解决了基于扩散模型的纹理失真问题，但存在底部检测不准确及合成结果中衣物轮廓残留等局限。为此，本文提出服装无关的预修补虚拟试衣方法CaP-VTON（Clothing Agnostic Pre-Inpainting Virtual Try-On）。该方法融合DressCode-based多类别掩码与Stable Diffusion-based皮肤膨胀预处理；特别引入生成皮肤模块，解决长袖转短袖或无袖时的皮肤修复问题，构建预处理结构以提升全身换装的自然性与一致性，支持姿态与颜色的高质量还原。实验表明，CaP-VTON在短袖合成准确率上达到92.5%，较Leffa提升15.4%，视觉评估中一致保持参考衣物的风格与形态。该结构具备模型无关特性，可适配各类基于扩散的虚拟试衣系统，对需高精度虚拟穿着的应用如电商、定制穿搭和虚拟角色创建具有重要价值。
原文摘要 · Abstract (English)
With the development of deep learning technology, virtual try-on technology has devel-oped important application value in the fields of e-commerce, fashion, and entertainment. The recently proposed Leffa technology has addressed the texture distortion problem of diffusion-based models, but there are limitations in that the bottom detection inaccuracy and the existing clothing silhouette persist in the synthesis results. To solve this problem, this study proposes CaP-VTON (Clothing Agnostic Pre-Inpainting Virtual Try-On). CaP-VTON integrates DressCode-based multi-category masking and Stable Diffu-sion-based skin inflation preprocessing; in particular, a generated skin module was in-troduced to solve skin restoration problems that occur when long-sleeved images are con-verted to short-sleeved or sleeveless ones, introducing a preprocessing structure that im-proves the naturalness and consistency of full-body clothing synthesis, and allowing the implementation of high-quality restoration considering human posture and color. As a result, CaP-VTON achieved 92.5%, which is 15.4% better than Leffa, in short-sleeved syn-thesis accuracy, and consistently reproduced the style and shape of the reference clothing in visual evaluation. These structures maintain model-agnostic properties and are appli-cable to various diffusion-based virtual inspection systems; they can also contribute to applications that require high-precision virtual wearing, such as e-commerce, custom styling, and avatar creation.
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。