PG-VTON：基于图像块引导参考对齐的单次免训练虚拟试衣
PG-VTON: Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment
把现成的图像修复扩散模型当作上下文补全器，仅用早期去噪步注入服装图像块、并在注意力层强化掩码区域 token 对服装 token 的关联，就能单次前向完成试衣；这套「不改权重、只调注入时机与注意力」的思路可直接迁移到其他参考图驱动的局部编辑任务。
原文依据 injects a localized garment patch only in early denoising steps to anchor garment identity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论虚拟试衣（VTON）旨在将目标服装渲染到人物身上，同时保持姿态、身份与细粒度外观。现有方法大多依赖有监督的成对数据，限制了跨域泛化能力；而近期的免训练方法虽然更鲁棒，却需要多次扩散调用与复杂的合成流程，难以实际部署。我们提出 PG-VTON，一个基于图像块引导参考对齐的单次免训练框架。我们的关键洞见是：现代图像修复扩散模型本身已具备强大的上下文补全能力——给定被掩码的人物图像和一小块服装图像块，它们无需任务特定训练即可合成合理且姿态一致的服装。PG-VTON 通过两个轻量组件利用这一能力：图像块锚定身份引导（PIP）仅在早期去噪步注入局部服装图像块以锚定服装身份，参考感知注意力（RAA）强化掩码区域 token 对服装 token 的注意力以增强细节迁移，且全程不修改模型权重。仅需一次扩散前向，PG-VTON 在 DressCode 与 VITON-HD 上取得了免训练方法中的最优性能，并能有效泛化到主体插入任务。代码见 https://github.com/PKU-ICST-MIPL/PG-VTON_CVPR2026。
英文原文摘要 1385 字符
Virtual try-on (VTON) aims to render a target garment onto a person while preserving pose, identity, and fine-grained appearance. Most existing methods rely on supervised paired data, limiting cross-domain generalization, while recent training-free approaches, though more robust, require multiple diffusion calls and complex compositing, making deployment impractical. We propose PG-VTON, a single-pass, training-free framework based on Patch-Guided Reference Alignment. Our key insight is that modern inpainting diffusion models already possess strong in-context completion: given a masked person and a small garment patch, they can synthesize plausible, pose-consistent clothing without task-specific training. PG-VTON exploits this capability with two lightweight components: Patch-Anchored Identity Priming (PIP) injects a localized garment patch only in early denoising steps to anchor garment identity, and Reference-Aware Attention (RAA) strengthens attention from masked-region tokens to garment tokens to enhance detail transfer, all without modifying model weights. With a single diffusion pass, PG-VTON achieves state-of-the-art performance among training-free methods on DressCode and VITON-HD and generalizes effectively to subject insertion. Code is available at \href https://github.com/PKU-ICST-MIPL/PG-VTON_CVPR2026 https://github.com/PKU-ICST-MIPL/PG-VTON_CVPR2026 .