用统一模型同时实现虚拟试穿和脱穿，提升穿搭匹配精度。
Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
- 单个扩散变换器联合学习试穿与试脱任务。
- 在多个基准上超越现有方法，对姿态变化更鲁棒。
- 适合服装设计、电商试穿等需要双向生成的场景。
虚拟试穿旨在合成人物穿戴目标衣物的真实图像，但准确建模衣物与人体的对应关系仍面临挑战，尤其在姿态和外观变化下。本文提出 Voost——一种统一且可扩展的框架，通过单一扩散变换器联合学习虚拟试穿与试脱。联合建模使每对衣物-人体相互监督双向生成，支持生成方向与衣物类别的灵活控制，无需专用网络、辅助损失或额外标签，增强衣物-人体关系推理能力。此外，引入两种推理时技术：注意力温度缩放以提升对分辨率或掩码变化的鲁棒性，自校正采样利用双向一致性进行优化。大量实验表明，Voost 在试穿与试脱基准上均达到最先进水平，一致优于强基线，在对齐精度、视觉保真度与泛化能力方面表现优异。
原文摘要 · Abstract (English)
Virtual try-on aims to synthesize a realistic image of a person wearing a target garment, but accurately modeling garment-body correspondence remains a persistent challenge, especially under pose and appearance variation. In this paper, we propose Voost - a unified and scalable framework that jointly learns virtual try-on and try-off with a single diffusion transformer. By modeling both tasks jointly, Voost enables each garment-person pair to supervise both directions and supports flexible conditioning over generation direction and garment category, enhancing garment-body relational reasoning without task-specific networks, auxiliary losses, or additional labels. In addition, we introduce two inference-time techniques: attention temperature scaling for robustness to resolution or mask variation, and self-corrective sampling that leverages bidirectional consistency between tasks. Extensive experiments demonstrate that Voost achieves state-of-the-art results on both try-on and try-off benchmarks, consistently outperforming strong baselines in alignment accuracy, visual fidelity, and generalization.
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。