FEAT：从任意设计源进行服装编辑与试穿
FEAT: Fashion Editing and Try-On from Any Design
Disentangled Dual Injection 的内容/风格解耦注入与 Orthogonal-Guided Noise Fusion 的正交投影去残留衣物+区域化噪声策略，是可复用到其他「保留身份/去除旧内容」的可控生成任务（如换装、换背景、局部重绘）的免训练手段。
原文依据 Orthogonal-Guided Noise Fusion (OGNF), a training-free mechanism that removes residual garments via orthogonal projection
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论服装设计旨在表达设计师的创作意图，并刻画服装与人体的交互方式。近期方法以多模态输入为条件，支持服装编辑与虚拟试穿。然而，现有方法仍然（i）将设计局限于与服装相关的图像，排除了艺术作品、抽象图像和自然照片等富有创意的设计来源；（ii）无法支持包括配饰在内的完整套装。我们提出 FEAT（Fashion Editing And Try-On from Any Design），一种能够利用多样化设计来源，在服装与配饰上同时实现编辑与试穿的方法。为此，我们引入解耦双注入（Disentangled Dual Injection, DDI）。它同时接收服装与非服装设计来源，并通过内容与风格的解耦，选择性地注入设计线索。此外，我们提出正交引导噪声融合（Orthogonal-Guided Noise Fusion, OGNF），这是一种免训练机制，通过正交投影去除残留衣物，并施加区域特定的噪声策略，从而为服装与配饰实现虚拟试穿。大量实验表明，FEAT 在设计灵活性、提示词一致性和视觉真实感方面均达到最优性能。
英文原文摘要 1200 字符
Fashion design aims to express a designer's creative intent and to depict how garments interact with the human body. Recent methods condition on multimodal inputs to support garment editing and virtual try-on. However, existing methods still (i) confine design to garment-related images, excluding creative design sources such as artwork, abstract imagery, and natural photographs, and (ii) cannot support complete outfits, including accessories. We present FEAT (Fashion Editing And Try-On from Any Design), a method that enables editing and try-on across garments and accessories using diverse design sources. To achieve this, we introduce Disentangled Dual Injection (DDI). It takes both apparel and non-apparel design sources and selectively injects design cues via content and style disentanglement. Furthermore, we propose Orthogonal-Guided Noise Fusion (OGNF), a training-free mechanism that removes residual garments via orthogonal projection and applies region-specific noise strategies to enable virtual try-on for both garments and accessories. Extensive experiments demonstrate that FEAT achieves state-of-the-art performance in design flexibility, prompt consistency, and visual realism.